
from pandas import DataFrame, Series
from io import StringIO
import pandas as pd
import numpy as np
import os
import matplotlib
import matplotlib.pyplot as plt
import plotly.express as px
from IPython.display import Image
import seaborn as sb
import statistics as stat
import time
import math
import tensorflow as tf
from sklearn.metrics import *
from sklearn.metrics import *
from sklearn import metrics
from sklearn.model_selection import GridSearchCV


from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split, GridSearchCV
from imblearn.over_sampling import RandomOverSampler
from sklearn.metrics import *
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import SGDClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.neural_network import MLPClassifier
from sklearn.experimental import enable_halving_search_cv
from sklearn.model_selection import HalvingGridSearchCV
from sklearn.ensemble import VotingClassifier, AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn import metrics
from sklearn.preprocessing import OrdinalEncoder
from imblearn.over_sampling import SMOTE
from sklearn.neural_network import MLPClassifier

from sklearn.ensemble import VotingClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import AdaBoostClassifier
from xgboost import XGBClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import StandardScaler
from keras.models import Sequential
from keras.layers import Dense


def describe(a):
    if type(a) is np.ndarray:
        print("data:\n{}\nshape:{}\ndtype:{}\ntype: {}".format(a, a.shape, a.dtype, type(a)))
    elif type(a) is pd.Series:
        print("data:\n{}\nshape:{}\ndtype:{}\nname:{}\nindex-name:{}\ntype:{}".format(a, a.shape, a.dtype, a.name, a.index.name, type(a)))
    elif type(a) is pd.DataFrame:
        print("data:\n{}\nshape:{}\ntype:{}".format(a, a.shape,type(a)))
    else:
        print("{}, type:{}".format(a, type(a)))


dataFrameWeather = pd.read_csv('./content/drive/MyDrive/weatherAUS.csv')


dataFrameWeather.shape

(145460, 23)


dataFrameWeather.describe()


dataFrameWeather.duplicated().value_counts()

False    145460
Name: count, dtype: int64


dataFrameWeather.sample(frac=1).head(30)


dataFrameWeather.isna().sum()

Date                 0
Location             0
MinTemp           1485
MaxTemp           1261
Rainfall          3261
Evaporation      62790
Sunshine         69835
WindGustDir      10326
WindGustSpeed    10263
WindDir9am       10566
WindDir3pm        4228
WindSpeed9am      1767
WindSpeed3pm      3062
Humidity9am       2654
Humidity3pm       4507
Pressure9am      15065
Pressure3pm      15028
Cloud9am         55888
Cloud3pm         59358
Temp9am           1767
Temp3pm           3609
RainToday         3261
RainTomorrow      3267
dtype: int64


import warnings
warnings.filterwarnings('ignore')
fig, ax = plt.subplots(figsize=(10, 10))
dataFrameWeather.hist(ax=ax)
plt.subplots_adjust(right=1.2, top=1.2)
plt.show()


mean_MinTemp = dataFrameWeather['MinTemp'].mean()
mean_MaxTemp = dataFrameWeather['MaxTemp'].mean()

dataFrameWeather['MinTemp'].fillna(mean_MinTemp, inplace=True)
dataFrameWeather['MaxTemp'].fillna(mean_MaxTemp, inplace=True)


dataFrameWeather.isna().sum()

Date                 0
Location             0
MinTemp              0
MaxTemp              0
Rainfall          3261
Evaporation      62790
Sunshine         69835
WindGustDir      10326
WindGustSpeed    10263
WindDir9am       10566
WindDir3pm        4228
WindSpeed9am      1767
WindSpeed3pm      3062
Humidity9am       2654
Humidity3pm       4507
Pressure9am      15065
Pressure3pm      15028
Cloud9am         55888
Cloud3pm         59358
Temp9am           1767
Temp3pm           3609
RainToday         3261
RainTomorrow      3267
dtype: int64


dataFrameWeather.dropna(subset='Rainfall', inplace=True)
dataFrameWeather.isna().sum()

Date                 0
Location             0
MinTemp              0
MaxTemp              0
Rainfall             0
Evaporation      60488
Sunshine         67820
WindGustDir       9725
WindGustSpeed     9665
WindDir9am        9789
WindDir3pm        3799
WindSpeed9am      1091
WindSpeed3pm      2647
Humidity9am       1554
Humidity3pm       3630
Pressure9am      13940
Pressure3pm      13993
Cloud9am         53331
Cloud3pm         56874
Temp9am            685
Temp3pm           2746
RainToday            0
RainTomorrow      1412
dtype: int64


dataFrameWeather = dataFrameWeather.drop(columns=['WindDir3pm', 'WindDir9am', 'WindSpeed3pm', 'WindSpeed9am'], axis=1)
dataFrameWeather.info()

<class 'pandas.core.frame.DataFrame'>
Index: 142199 entries, 0 to 145459
Data columns (total 19 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Date           142199 non-null  object 
 1   Location       142199 non-null  object 
 2   MinTemp        142199 non-null  float64
 3   MaxTemp        142199 non-null  float64
 4   Rainfall       142199 non-null  float64
 5   Evaporation    81711 non-null   float64
 6   Sunshine       74379 non-null   float64
 7   WindGustDir    132474 non-null  object 
 8   WindGustSpeed  132534 non-null  float64
 9   Humidity9am    140645 non-null  float64
 10  Humidity3pm    138569 non-null  float64
 11  Pressure9am    128259 non-null  float64
 12  Pressure3pm    128206 non-null  float64
 13  Cloud9am       88868 non-null   float64
 14  Cloud3pm       85325 non-null   float64
 15  Temp9am        141514 non-null  float64
 16  Temp3pm        139453 non-null  float64
 17  RainToday      142199 non-null  object 
 18  RainTomorrow   140787 non-null  object 
dtypes: float64(14), object(5)
memory usage: 21.7+ MB


dataFrameWeather.dropna(subset='RainTomorrow', inplace=True)
plt.figure(figsize=(5,6))
ax = sb.countplot(x='RainTomorrow', data=dataFrameWeather, palette="Set1")
plt.show()
dataFrameWeather.info()

<class 'pandas.core.frame.DataFrame'>
Index: 140787 entries, 0 to 145458
Data columns (total 19 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Date           140787 non-null  object 
 1   Location       140787 non-null  object 
 2   MinTemp        140787 non-null  float64
 3   MaxTemp        140787 non-null  float64
 4   Rainfall       140787 non-null  float64
 5   Evaporation    81093 non-null   float64
 6   Sunshine       73982 non-null   float64
 7   WindGustDir    131624 non-null  object 
 8   WindGustSpeed  131682 non-null  float64
 9   Humidity9am    139270 non-null  float64
 10  Humidity3pm    137286 non-null  float64
 11  Pressure9am    127044 non-null  float64
 12  Pressure3pm    127018 non-null  float64
 13  Cloud9am       88162 non-null   float64
 14  Cloud3pm       84693 non-null   float64
 15  Temp9am        140131 non-null  float64
 16  Temp3pm        138163 non-null  float64
 17  RainToday      140787 non-null  object 
 18  RainTomorrow   140787 non-null  object 
dtypes: float64(14), object(5)
memory usage: 21.5+ MB


average_humidity = dataFrameWeather.groupby('RainToday')['Humidity9am'].transform('mean')
average_humidity2 = dataFrameWeather.groupby('RainToday')['Humidity3pm'].transform('mean')
average_temp = dataFrameWeather.groupby('RainToday')['Temp9am'].transform('mean')
average_temp2 = dataFrameWeather.groupby('RainToday')['Temp3pm'].transform('mean')
dataFrameWeather['Humidity9am'].fillna(average_humidity, inplace=True)
dataFrameWeather['Humidity3pm'].fillna(average_humidity2, inplace=True)
dataFrameWeather['Temp9am'].fillna(average_temp, inplace=True)
dataFrameWeather['Temp3pm'].fillna(average_temp2, inplace=True)


dataFrameWeather.isna().sum()

Date                 0
Location             0
MinTemp              0
MaxTemp              0
Rainfall             0
Evaporation      59694
Sunshine         66805
WindGustDir       9163
WindGustSpeed     9105
Humidity9am          0
Humidity3pm          0
Pressure9am      13743
Pressure3pm      13769
Cloud9am         52625
Cloud3pm         56094
Temp9am              0
Temp3pm              0
RainToday            0
RainTomorrow         0
dtype: int64


plt.figure(figsize=(13,10))

plt.subplot(2, 2, 1)
fig = dataFrameWeather.Rainfall.hist(bins=10)
fig.set_xlabel('Rainfall')
fig.set_ylabel('RainTomorrow')

plt.subplot(2, 2, 2)
fig = dataFrameWeather.WindGustSpeed.hist(bins=10)
fig.set_xlabel('WinGustSpeed')
fig.set_ylabel('RainTomorrow')

plt.subplot(2, 2, 3)
fig = dataFrameWeather.Temp3pm.hist(bins=10)
fig.set_xlabel('Temp3pm')
fig.set_ylabel('RainTomorrow')

plt.subplot(2, 2, 4)
fig = dataFrameWeather.Humidity3pm.hist(bins=10)
fig.set_xlabel('Humidity')
fig.set_ylabel('RainTomorrow')

Text(0, 0.5, 'RainTomorrow')


dataFrameWeather = dataFrameWeather.drop(columns=['Sunshine'], axis=1)
dataFrameWeather.info()

<class 'pandas.core.frame.DataFrame'>
Index: 140787 entries, 0 to 145458
Data columns (total 18 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Date           140787 non-null  object 
 1   Location       140787 non-null  object 
 2   MinTemp        140787 non-null  float64
 3   MaxTemp        140787 non-null  float64
 4   Rainfall       140787 non-null  float64
 5   Evaporation    81093 non-null   float64
 6   WindGustDir    131624 non-null  object 
 7   WindGustSpeed  131682 non-null  float64
 8   Humidity9am    140787 non-null  float64
 9   Humidity3pm    140787 non-null  float64
 10  Pressure9am    127044 non-null  float64
 11  Pressure3pm    127018 non-null  float64
 12  Cloud9am       88162 non-null   float64
 13  Cloud3pm       84693 non-null   float64
 14  Temp9am        140787 non-null  float64
 15  Temp3pm        140787 non-null  float64
 16  RainToday      140787 non-null  object 
 17  RainTomorrow   140787 non-null  object 
dtypes: float64(13), object(5)
memory usage: 20.4+ MB


dataFrameWeather.isna().sum()

Date                 0
Location             0
MinTemp              0
MaxTemp              0
Rainfall             0
Evaporation      59694
WindGustDir       9163
WindGustSpeed     9105
Humidity9am          0
Humidity3pm          0
Pressure9am      13743
Pressure3pm      13769
Cloud9am         52625
Cloud3pm         56094
Temp9am              0
Temp3pm              0
RainToday            0
RainTomorrow         0
dtype: int64


df_copy = dataFrameWeather.copy()
# Aggiungo la colonna "month" al dataframe
df_copy['day'] = df_copy.Date.str.split("-", expand = True)[0]
df_copy['month'] = df_copy.Date.str.split("-", expand = True)[1]
# Aggiungo la colonna "year" al dataframe
df_copy['year'] = df_copy.Date.str.split("-", expand = True)[2]
df_copy = df_copy.drop(columns='Date', axis=1)


df_copy.isna().sum()

Location             0
MinTemp              0
MaxTemp              0
Rainfall             0
Evaporation      59694
WindGustDir       9163
WindGustSpeed     9105
Humidity9am          0
Humidity3pm          0
Pressure9am      13743
Pressure3pm      13769
Cloud9am         52625
Cloud3pm         56094
Temp9am              0
Temp3pm              0
RainToday            0
RainTomorrow         0
day                  0
month                0
year                 0
dtype: int64


df_num = df_copy.select_dtypes(include=[np.number])
df_cat = df_copy.select_dtypes(include=['object'])


for attr in df_cat.columns:
    df_cat[attr] = LabelEncoder().fit_transform(df_cat[attr])
df_encoded = pd.concat([df_cat, df_num], axis = 1)
df_encoded.head()


df_encoded.info()

<class 'pandas.core.frame.DataFrame'>
Index: 140787 entries, 0 to 145458
Data columns (total 20 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Location       140787 non-null  int32  
 1   WindGustDir    140787 non-null  int32  
 2   RainToday      140787 non-null  int32  
 3   RainTomorrow   140787 non-null  int32  
 4   day            140787 non-null  int32  
 5   month          140787 non-null  int32  
 6   year           140787 non-null  int32  
 7   MinTemp        140787 non-null  float64
 8   MaxTemp        140787 non-null  float64
 9   Rainfall       140787 non-null  float64
 10  Evaporation    81093 non-null   float64
 11  WindGustSpeed  131682 non-null  float64
 12  Humidity9am    140787 non-null  float64
 13  Humidity3pm    140787 non-null  float64
 14  Pressure9am    127044 non-null  float64
 15  Pressure3pm    127018 non-null  float64
 16  Cloud9am       88162 non-null   float64
 17  Cloud3pm       84693 non-null   float64
 18  Temp9am        140787 non-null  float64
 19  Temp3pm        140787 non-null  float64
dtypes: float64(13), int32(7)
memory usage: 18.8 MB


from sklearn.experimental import enable_iterative_imputer
from sklearn.impute import IterativeImputer

imputer = IterativeImputer()
df_imputed = df_encoded.copy()
df_imputed = imputer.fit_transform(df_imputed) #imputation dei valori mancanti
df_imputed = pd.DataFrame(df_imputed, columns=df_encoded.columns) #conversione in dataframe pandas
df_imputed.head(100)


df_imputed.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 140787 entries, 0 to 140786
Data columns (total 20 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Location       140787 non-null  float64
 1   WindGustDir    140787 non-null  float64
 2   RainToday      140787 non-null  float64
 3   RainTomorrow   140787 non-null  float64
 4   day            140787 non-null  float64
 5   month          140787 non-null  float64
 6   year           140787 non-null  float64
 7   MinTemp        140787 non-null  float64
 8   MaxTemp        140787 non-null  float64
 9   Rainfall       140787 non-null  float64
 10  Evaporation    140787 non-null  float64
 11  WindGustSpeed  140787 non-null  float64
 12  Humidity9am    140787 non-null  float64
 13  Humidity3pm    140787 non-null  float64
 14  Pressure9am    140787 non-null  float64
 15  Pressure3pm    140787 non-null  float64
 16  Cloud9am       140787 non-null  float64
 17  Cloud3pm       140787 non-null  float64
 18  Temp9am        140787 non-null  float64
 19  Temp3pm        140787 non-null  float64
dtypes: float64(20)
memory usage: 21.5 MB


df_imputed['Location'] = df_imputed['Location'].astype(int)
df_imputed['WindGustDir'] = df_imputed['WindGustDir'].astype(int)
df_imputed['RainTomorrow'] = df_imputed['RainTomorrow'].astype(int)
df_imputed['RainToday'] = df_imputed['RainToday'].astype(int)
df_imputed['day'] = df_imputed['day'].astype(int)
df_imputed['month'] = df_imputed['month'].astype(int)
df_imputed['year'] = df_imputed['year'].astype(int)
df_imputed.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 140787 entries, 0 to 140786
Data columns (total 20 columns):
 #   Column         Non-Null Count   Dtype  
---  ------         --------------   -----  
 0   Location       140787 non-null  int32  
 1   WindGustDir    140787 non-null  int32  
 2   RainToday      140787 non-null  int32  
 3   RainTomorrow   140787 non-null  int32  
 4   day            140787 non-null  int32  
 5   month          140787 non-null  int32  
 6   year           140787 non-null  int32  
 7   MinTemp        140787 non-null  float64
 8   MaxTemp        140787 non-null  float64
 9   Rainfall       140787 non-null  float64
 10  Evaporation    140787 non-null  float64
 11  WindGustSpeed  140787 non-null  float64
 12  Humidity9am    140787 non-null  float64
 13  Humidity3pm    140787 non-null  float64
 14  Pressure9am    140787 non-null  float64
 15  Pressure3pm    140787 non-null  float64
 16  Cloud9am       140787 non-null  float64
 17  Cloud3pm       140787 non-null  float64
 18  Temp9am        140787 non-null  float64
 19  Temp3pm        140787 non-null  float64
dtypes: float64(13), int32(7)
memory usage: 17.7 MB


warnings.filterwarnings('ignore')
fig, ax = plt.subplots(figsize=(10, 10))
df_imputed.hist(ax=ax)
plt.subplots_adjust(right=1.2, top=1.2)
plt.show()


num = ['Humidity3pm', 'Humidity9am', 'Temp3pm', 'MinTemp', 'MaxTemp', 'Temp9am']
sb.pairplot(df_imputed[num], kind='scatter', diag_kind='hist', palette='Rainbow')
plt.show()


df_imputed.shape

(140787, 20)


from sklearn.cluster import DBSCAN
from sklearn.preprocessing import StandardScaler

# Standardize the features
scaler = StandardScaler()
df_scaled = scaler.fit_transform(df_imputed)

# Create DBSCAN object
dbscan = DBSCAN(eps=1.5, min_samples=4)

# Perform clustering
clusters = dbscan.fit_predict(df_scaled)

# Add the cluster labels to the DataFrame
df_imputed['Cluster'] = clusters
df_imputed[df_imputed['Cluster'] == -1].sum()

#df_no_outliers = df_imputed[clusters != -1]
# Visualize the clusters
plt.scatter(df_imputed['Temp9am'], df_imputed['Temp3pm'], c=df_imputed['Cluster'], cmap='viridis')
plt.xlabel('Temp9am')
plt.ylabel('Temp3pm')
plt.title('DBSCAN Clustering')
plt.show()


df_imputed = df_imputed[clusters != -1]

plt.scatter(df_imputed['Temp9am'], df_imputed['Temp3pm'], c=df_imputed['Cluster'], cmap='viridis')
plt.xlabel('Temp9am')
plt.ylabel('Temp3pm')
plt.title('DBSCAN Clustering')
plt.show()


df_imputed = df_imputed.drop(columns=['Cluster'], axis=1)


num = ['Humidity3pm', 'Humidity9am', 'Temp3pm', 'MinTemp', 'MaxTemp', 'Temp9am']
sb.pairplot(df_imputed[num], kind='scatter', diag_kind='hist', palette='Rainbow')
plt.show()


df_imputed.shape

(79102, 20)


#creo la matrice di correlazione
matr_corr = df_imputed.corr()

#stampo la matrice di correlazione
plt.figure(figsize=(12,12))
sb.heatmap(matr_corr, annot=True, cmap='coolwarm', fmt=".2f")
plt.show()


df_X = df_imputed.drop(['RainTomorrow'], axis=1)
df_Y = df_imputed['RainTomorrow']

forest = RandomForestClassifier()
forest.fit(df_X, df_Y)

attributi= df_X.columns
importances= forest.feature_importances_ #grado di importanza fra gli attributi
index= np.argsort(importances) #mappa ogni grado di importanza con l'attributo corrispondente

plt.figure(figsize=(10,10))
plt.title('Grado di importanza fra gli attributi')
plt.barh(range(len(index)),importances[index],color='r',align='center')
plt.yticks(range(len(index)),attributi[index])
plt.show()


df_imputed.shape

(79102, 20)


df_imputed = df_imputed.drop(['day', 'month', 'year', 'Location', 'WindGustDir', 'Temp9am', 'MinTemp'], axis=1)


plt.figure(figsize=(4, 4))
ax = sb.countplot(x=df_imputed['RainTomorrow'])
plt.bar_label(ax.containers[0])
plt.show()


X = df_imputed.drop(['RainTomorrow'], axis=1)
y = df_imputed['RainTomorrow']

#Utilizzo lo smote per fare oversampling e aumentare il numero di istanze 'RainTomorrow' = 'Yes' (1)
smote = SMOTE(random_state=35)
X_smoted, y_smoted = smote.fit_resample(X,y)
df_balanced = pd.concat([X_smoted, y_smoted],axis=1)

plt.figure(figsize=(4, 4))
ax = sb.countplot(x=df_balanced['RainTomorrow'])
plt.bar_label(ax.containers[0])
plt.show()


df_balanced.shape

(141524, 13)


df_balanced.to_csv('df_final.csv', index=False)


image = 'confusion_matrix.png'
Image(filename=os.path.join(image),width=300)


image2 = 'auc-roc.png'
Image(filename=os.path.join(image2),width=350)


# data frame per risultati dei modelli per la cross-validation
results= pd.DataFrame(columns=['NomeModello','Accuracy','ErrorRate','Precision','Recall','F-score','Time'])


def valuta_performance(nomeModello, modello, X, y, data,temp):
    indici = data[data['NomeModello'] == nomeModello].index
    for j in range(len(indici)):
        data.drop(indici[j], inplace = True)
    accuracy = cross_val_score(modello, X ,y, cv=10 ,scoring="accuracy").mean()
    error = (1-accuracy)
    precision = cross_val_score(modello, X ,y, cv=10 ,scoring="average_precision").mean()
    recall = cross_val_score(modello, X ,y, cv=10 ,scoring="recall_micro").mean()
    f_score = cross_val_score(modello, X ,y, cv=10 ,scoring="f1_micro").mean()

    row = pd.DataFrame({'NomeModello': [nomeModello],
                        'Accuracy': [accuracy],
                        'ErrorRate': [error],
                        'Precision': [precision],
                        'Recall': [recall],
                        'F-score': [f_score],
                        'Time': [temp]})

    data = pd.concat([data, row], ignore_index=True)

    return data


# dataframe utili per il plotting delle performance dei classificatori
models=["Albero_Decisionale", "Albero_Decisionale_CV", "Naive_Bayes","Naive_Bayes_CV", "LogReg","LogReg_CV", "KNN","KNN_CV","SGD", "SGD_CV", "Voting", "Random_Forest","AdaBoost",'XGBoost']
results_test= pd.DataFrame(index=models,columns=["accuracy","balanced_accuracy","precision","w_precision","recall","w_recall","f1"])
results_train= pd.DataFrame(index=models,columns=["accuracy","balanced_accuracy","precision","w_precision","recall","w_recall","f1"])


# dataframe specifico per le ANN
models_neural=["ANN","MLP"]
results_test_neural= pd.DataFrame(index=models_neural,columns=["accuracy","balanced_accuracy","precision","w_precision","recall","w_recall","f1"])


# funzione per salvare gli score dei relativi modelli
def set_scores(df,model,label,predicted):
    df.loc[model]["f1"]=f1_score(label, predicted)
    df.loc[model]["accuracy"]=accuracy_score(label, predicted)
    df.loc[model]["recall"]=recall_score(label, predicted)
    df.loc[model]["precision"]=precision_score(label, predicted)
    df.loc[model]["balanced_accuracy"]=balanced_accuracy_score(label, predicted)
    df.loc[model]["w_recall"]=recall_score(label, predicted,average='weighted')
    df.loc[model]["w_precision"]=precision_score(label, predicted,average='weighted')


# Lista degli score per la ROC
lista_predizioni = []


df_final = pd.read_csv('df_final.csv')


#Divido il dataset in test_set e training_set
df_X = df_final.drop('RainTomorrow', axis=1)
df_y = df_final['RainTomorrow']

X_train,X_test,y_train,y_test = train_test_split(df_X, df_y, test_size=.33, random_state=42)
y_train = y_train.values.ravel()


start = time.time()
albero = DecisionTreeClassifier(random_state=42, max_depth=15)
albero = albero.fit(X_train, y_train)
stop = time.time()-start


result = valuta_performance('Albero Decisionale', albero, X_train, y_train, results, stop)


y_pred_train_albero = albero.predict(X_train)
confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_albero)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_albero))

              precision    recall  f1-score   support

           0       0.99      0.98      0.98     47408
           1       0.98      0.99      0.98     47413

    accuracy                           0.98     94821
   macro avg       0.98      0.98      0.98     94821
weighted avg       0.98      0.98      0.98     94821


set_scores(results_train, "Albero_Decisionale", y_train, y_pred_train_albero)


y_pred_test_albero=albero.predict(X_test)
lista_predizioni.append(y_pred_test_albero)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_albero)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_albero))

              precision    recall  f1-score   support

           0       0.95      0.94      0.95     23354
           1       0.94      0.95      0.95     23349

    accuracy                           0.95     46703
   macro avg       0.95      0.95      0.95     46703
weighted avg       0.95      0.95      0.95     46703


set_scores(results_test, "Albero_Decisionale", y_test, y_pred_test_albero)


print("max_features: ", albero.max_features_)
print("max_depth: ", albero.tree_.max_depth)
print("min_samples_split: ", albero.min_samples_split)
print("min_samples_leaf: ", albero.min_samples_leaf)

max_features:  12
max_depth:  15
min_samples_split:  2
min_samples_leaf:  1


albero_grid_search = DecisionTreeClassifier()

grid = {'max_features': ['sqrt', 'log2'],
        'max_depth': [12, 14, 16],
        'min_samples_split': [2, 4, 5],
        'min_samples_leaf': [2, 3, 5],
        'criterion':['gini','entropy'],
        'splitter':['best','random'],
       }

grid_search = GridSearchCV(
                estimator=albero_grid_search,
                param_grid=grid,
                cv=5,
                scoring="recall", #ci interessa la recall rispetto alla precision
                n_jobs=-1)

grid_search_result = grid_search.fit(X_train, y_train)

albero_grid_search = grid_search.best_estimator_
print(albero_grid_search)

DecisionTreeClassifier(max_depth=16, max_features='log2', min_samples_leaf=3,
                       min_samples_split=5)


y_pred_train_albero_grid_search = albero_grid_search.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_albero_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_albero_grid_search))

              precision    recall  f1-score   support

           0       0.97      0.96      0.97     47408
           1       0.96      0.97      0.97     47413

    accuracy                           0.97     94821
   macro avg       0.97      0.97      0.97     94821
weighted avg       0.97      0.97      0.97     94821


set_scores(results_train, "Albero_Decisionale_CV", y_train, y_pred_train_albero_grid_search)


y_pred_test_albero_grid_search = albero_grid_search.predict(X_test)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_albero_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_albero_grid_search))

              precision    recall  f1-score   support

           0       0.94      0.93      0.93     23354
           1       0.93      0.94      0.93     23349

    accuracy                           0.93     46703
   macro avg       0.93      0.93      0.93     46703
weighted avg       0.93      0.93      0.93     46703


set_scores(results_test, "Albero_Decisionale_CV", y_train, y_pred_train_albero_grid_search)


start = time.time()
nb = GaussianNB()
nb = nb.fit(X_train, y_train)
stop = time.time() - start


results = valuta_performance("Naive Bayes Gaussian", nb, X_train, y_train, results, stop)


y_pred_train_bayes = nb.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_bayes)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_bayes))

              precision    recall  f1-score   support

           0       0.83      0.86      0.84     47408
           1       0.85      0.82      0.84     47413

    accuracy                           0.84     94821
   macro avg       0.84      0.84      0.84     94821
weighted avg       0.84      0.84      0.84     94821


set_scores(results_train,"Naive_Bayes", y_train, y_pred_train_bayes)


y_pred_test_bayes = nb.predict(X_test)
lista_predizioni.append(y_pred_test_bayes)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_bayes)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_bayes))

              precision    recall  f1-score   support

           0       0.83      0.85      0.84     23354
           1       0.85      0.83      0.84     23349

    accuracy                           0.84     46703
   macro avg       0.84      0.84      0.84     46703
weighted avg       0.84      0.84      0.84     46703


set_scores(results_test, "Naive_Bayes", y_test, y_pred_test_bayes)
print("var_smoothing: " + str(nb.var_smoothing))

var_smoothing: 1e-09


naive_bayes_search_grid = GaussianNB()

grid_param = {'var_smoothing': [1e-010, 1e-09, 1e-08]}

grid_search = GridSearchCV(
    estimator=nb,
    param_grid=grid_param,
    cv=5,
    scoring="recall",
    n_jobs=-1
)

grid_search.fit(X_train,y_train)

naive_bayes_search_grid=grid_search.best_estimator_
print(grid_search.best_estimator_)

GaussianNB(var_smoothing=1e-10)


y_train_naive_bayes_grid_search=naive_bayes_search_grid.predict(X_train)
confusion_matrix = metrics.confusion_matrix(y_train,y_train_naive_bayes_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_train_naive_bayes_grid_search))

              precision    recall  f1-score   support

           0       0.83      0.86      0.84     47408
           1       0.85      0.82      0.84     47413

    accuracy                           0.84     94821
   macro avg       0.84      0.84      0.84     94821
weighted avg       0.84      0.84      0.84     94821


set_scores(results_train,"Naive_Bayes_CV",y_train,y_train_naive_bayes_grid_search)


y_test_naive_bayes_grid_search=naive_bayes_search_grid.predict(X_test)
lista_predizioni.append(y_test_naive_bayes_grid_search)


confusion_matrix = metrics.confusion_matrix(y_test,y_test_naive_bayes_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_test_naive_bayes_grid_search))

              precision    recall  f1-score   support

           0       0.83      0.85      0.84     23354
           1       0.85      0.83      0.84     23349

    accuracy                           0.84     46703
   macro avg       0.84      0.84      0.84     46703
weighted avg       0.84      0.84      0.84     46703


set_scores(results_test,"Naive_Bayes_CV",y_test,y_test_naive_bayes_grid_search)


start= time.time()
logreg = LogisticRegression(random_state=42,max_iter=500) #aumento iterazioni per la convergenza dell'algoritmo
logreg = logreg.fit(X_train, y_train)
stop= time.time()-start


results= valuta_performance('Logistic Regression', logreg, X_train, y_train, results, stop)


y_pred_train_logreg = logreg.predict(X_train)
confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_logreg)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_logreg))

              precision    recall  f1-score   support

           0       0.87      0.85      0.86     47408
           1       0.86      0.88      0.87     47413

    accuracy                           0.86     94821
   macro avg       0.86      0.86      0.86     94821
weighted avg       0.86      0.86      0.86     94821


set_scores(results_train, 'LogReg', y_train, y_pred_train_logreg)


y_pred_test_logreg = logreg.predict(X_test)
lista_predizioni.append(y_pred_test_logreg)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_logreg)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_logreg))

              precision    recall  f1-score   support

           0       0.87      0.85      0.86     23354
           1       0.85      0.88      0.86     23349

    accuracy                           0.86     46703
   macro avg       0.86      0.86      0.86     46703
weighted avg       0.86      0.86      0.86     46703


set_scores(results_test, "LogReg", y_test, y_pred_test_logreg)


logistic_regression_grid_search = LogisticRegression(random_state=42, max_iter=500)

param_grid = {
    'C': [10,1.0,0.1],
    'solver': ['newton-cg'],
    'penalty': ['l2']
}

grid_search = GridSearchCV(
    estimator=logistic_regression_grid_search,
    param_grid=param_grid,
    n_jobs=-1,
    cv=5,
    scoring="recall"
)

grid_final = grid_search.fit(X_train,y_train)

logistic_regression_grid_search = grid_search.best_estimator_
print(grid_search.best_estimator_)

LogisticRegression(C=10, max_iter=500, random_state=42, solver='newton-cg')


y_pred_train_logistic_regression = logistic_regression_grid_search.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_logistic_regression)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_logistic_regression))

              precision    recall  f1-score   support

           0       0.88      0.86      0.87     47408
           1       0.86      0.88      0.87     47413

    accuracy                           0.87     94821
   macro avg       0.87      0.87      0.87     94821
weighted avg       0.87      0.87      0.87     94821


set_scores(results_train, "LogReg_CV", y_train, y_pred_train_logistic_regression)


y_pred_test_logistic_regression = logistic_regression_grid_search.predict(X_test)


lista_predizioni.append(y_pred_test_logistic_regression)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_logistic_regression)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_logistic_regression))

              precision    recall  f1-score   support

           0       0.88      0.86      0.87     23354
           1       0.86      0.88      0.87     23349

    accuracy                           0.87     46703
   macro avg       0.87      0.87      0.87     46703
weighted avg       0.87      0.87      0.87     46703


set_scores(results_test,"LogReg_CV",y_test,y_pred_test_logistic_regression)


start= time.time()
Knn = KNeighborsClassifier(n_neighbors=5)
Knn = Knn.fit(X_train,y_train)
stop= time.time()-start


import warnings
warnings.filterwarnings('ignore')
results= valuta_performance('KNN classifier', Knn, X_train, y_train, results,stop)


y_pred_train_Knn = Knn.predict(X_train)
lista_predizioni.append(y_pred_train_Knn)
confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_Knn)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_Knn))

              precision    recall  f1-score   support

           0       1.00      0.89      0.94     47408
           1       0.90      1.00      0.95     47413

    accuracy                           0.94     94821
   macro avg       0.95      0.94      0.94     94821
weighted avg       0.95      0.94      0.94     94821


set_scores(results_train, "KNN", y_train, y_pred_train_Knn)


y_pred_test_Knn = Knn.predict(X_test)


#lista_predizioni.append(y_pred_test_Knn)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_Knn)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_Knn))

              precision    recall  f1-score   support

           0       0.99      0.85      0.92     23354
           1       0.87      0.99      0.93     23349

    accuracy                           0.92     46703
   macro avg       0.93      0.92      0.92     46703
weighted avg       0.93      0.92      0.92     46703


set_scores(results_test, "KNN", y_test, y_pred_test_Knn)
print("n_neighbors: " + str(Knn.n_neighbors))
print("leaf_size: " + str(Knn.leaf_size))

n_neighbors: 5
leaf_size: 30


knn_grid_search = KNeighborsClassifier()

param_grid = {
    'n_neighbors': [2,3,4,5],
    'leaf_size': [1,2,3,4]
}

grid_search = GridSearchCV(
                estimator=knn_grid_search,
                param_grid=param_grid,
                cv=5,
                scoring="recall",
                n_jobs=-1
)

grid_search_result = grid_search.fit(X_train, y_train)

knn_grid_search = grid_search.fit(X_train, y_train)
print(grid_search.best_estimator_)

KNeighborsClassifier(leaf_size=1, n_neighbors=3)


y_pred_train_knn_grid_search = knn_grid_search.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_knn_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_knn_grid_search))

              precision    recall  f1-score   support

           0       1.00      0.92      0.96     47408
           1       0.93      1.00      0.96     47413

    accuracy                           0.96     94821
   macro avg       0.96      0.96      0.96     94821
weighted avg       0.96      0.96      0.96     94821


set_scores(results_train, "KNN_CV", y_train,y_pred_train_knn_grid_search)


y_pred_test_knn_grid_search = knn_grid_search.predict(X_test)


lista_predizioni.append(y_pred_test_knn_grid_search)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_knn_grid_search)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_knn_grid_search))

              precision    recall  f1-score   support

           0       1.00      0.87      0.93     23354
           1       0.88      1.00      0.94     23349

    accuracy                           0.93     46703
   macro avg       0.94      0.93      0.93     46703
weighted avg       0.94      0.93      0.93     46703


set_scores(results_test, "KNN_CV", y_test, y_pred_test_knn_grid_search)


start = time.time()
SGD = SGDClassifier(max_iter=5000, random_state=42)
SGD = SGD.fit(X_train, y_train)
stop = time.time() - start


results = valuta_performance('SGD', SGD, X_train, y_train, results, stop)


y_pred_train_SGD = SGD.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_SGD)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_SGD))

              precision    recall  f1-score   support

           0       0.97      0.67      0.79     47408
           1       0.75      0.98      0.85     47413

    accuracy                           0.83     94821
   macro avg       0.86      0.83      0.82     94821
weighted avg       0.86      0.83      0.82     94821


set_scores(results_train, "SGD", y_train, y_pred_train_SGD)


y_pred_test_SGD = SGD.predict(X_test)


lista_predizioni.append(y_pred_test_SGD)


confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_SGD)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_SGD))

              precision    recall  f1-score   support

           0       0.97      0.67      0.79     23354
           1       0.75      0.98      0.85     23349

    accuracy                           0.82     46703
   macro avg       0.86      0.82      0.82     46703
weighted avg       0.86      0.82      0.82     46703


set_scores(results_test, "SGD", y_test, y_pred_test_SGD)
print("alpha: " + str(SGD.alpha))

alpha: 0.0001


sgd_grid_search = SGDClassifier()

grid = {
    'loss': ['hinge', 'log_loss', 'squared_hinge', 'modified_huber', "perceptron"],
    'alpha': [0.00001, 0.0001, 0.001, 0.01],
    'penalty': ['l1', 'l2', 'elasticnet']
}
grid_search = GridSearchCV(
                estimator=sgd_grid_search,
                param_grid=grid,
                cv=5,
                scoring="recall",
                n_jobs=-1
)
grid_result = grid_search.fit(X_train, y_train)

sgd_grid_search = grid_search.best_estimator_
print(grid_search.best_estimator_)

SGDClassifier(loss='perceptron', penalty='elasticnet')


y_pred_train_SGD_grid_search = sgd_grid_search.predict(X_train)
confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_SGD_grid_search)
cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_SGD_grid_search))

              precision    recall  f1-score   support

           0       0.96      0.71      0.82     47408
           1       0.77      0.97      0.86     47413

    accuracy                           0.84     94821
   macro avg       0.86      0.84      0.84     94821
weighted avg       0.86      0.84      0.84     94821


set_scores(results_train,"SGD_CV",y_train,y_pred_train_SGD_grid_search)


y_pred_test_SGD_grid_search = sgd_grid_search.predict(X_test)
lista_predizioni.append(y_pred_test_SGD_grid_search)
confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_SGD_grid_search)
cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_SGD_grid_search))

              precision    recall  f1-score   support

           0       0.96      0.71      0.81     23354
           1       0.77      0.97      0.86     23349

    accuracy                           0.84     46703
   macro avg       0.86      0.84      0.83     46703
weighted avg       0.86      0.84      0.83     46703


set_scores(results_test,"SGD_CV",y_test,y_pred_test_SGD_grid_search)


voting = VotingClassifier(estimators=[('k-nearest neighbors', Knn),('regressione logistica', logreg),('classficatore bayesiano', nb)], voting ='hard')
voting.fit(X_train,y_train)

VotingClassifier(estimators=[('k-nearest neighbors', KNeighborsClassifier()),
                             ('regressione logistica',
                              LogisticRegression(max_iter=500,
                                                 random_state=42)),
                             ('classficatore bayesiano', GaussianNB())])

VotingClassifier(estimators=[('k-nearest neighbors', KNeighborsClassifier()),
                             ('regressione logistica',
                              LogisticRegression(max_iter=500,
                                                 random_state=42)),
                             ('classficatore bayesiano', GaussianNB())])

KNeighborsClassifier()

LogisticRegression(max_iter=500, random_state=42)

GaussianNB()


y_train_voting=voting.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train, y_train_voting)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_train_voting))

              precision    recall  f1-score   support

           0       0.90      0.88      0.89     47408
           1       0.88      0.90      0.89     47413

    accuracy                           0.89     94821
   macro avg       0.89      0.89      0.89     94821
weighted avg       0.89      0.89      0.89     94821


set_scores(results_train,"Voting", y_train, y_train_voting)


y_test_voting=voting.predict(X_test)


lista_predizioni.append(y_test_voting)


confusion_matrix = metrics.confusion_matrix(y_test, y_test_voting)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_test_voting))

              precision    recall  f1-score   support

           0       0.90      0.87      0.88     23354
           1       0.87      0.90      0.89     23349

    accuracy                           0.88     46703
   macro avg       0.88      0.88      0.88     46703
weighted avg       0.88      0.88      0.88     46703


set_scores(results_test,"Voting",y_test,y_test_voting)


forest = RandomForestClassifier(random_state=42, max_depth=13)
forest = forest.fit(X_train,y_train)


y_pred_train_forest = forest.predict(X_train)
lista_predizioni.append(y_pred_train_forest)
confusion_matrix = metrics.confusion_matrix(y_train,y_pred_train_forest)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_pred_train_forest))

              precision    recall  f1-score   support

           0       0.99      0.97      0.98     47408
           1       0.97      0.99      0.98     47413

    accuracy                           0.98     94821
   macro avg       0.98      0.98      0.98     94821
weighted avg       0.98      0.98      0.98     94821


set_scores(results_train, "Random_Forest", y_train, y_pred_train_forest)


y_pred_test_forest = forest.predict(X_test)
lista_predizioni.append(y_pred_test_forest)
confusion_matrix = metrics.confusion_matrix(y_test,y_pred_test_forest)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_pred_test_forest))

              precision    recall  f1-score   support

           0       0.97      0.95      0.96     23354
           1       0.95      0.97      0.96     23349

    accuracy                           0.96     46703
   macro avg       0.96      0.96      0.96     46703
weighted avg       0.96      0.96      0.96     46703


set_scores(results_test, "Random_Forest", y_test, y_pred_test_forest)
print("n_estimators: " + str(forest.n_estimators))
print("min_samples_split: " + str(forest.min_samples_split))
print("min_samples_leaf: " + str(forest.min_samples_leaf))

n_estimators: 100
min_samples_split: 2
min_samples_leaf: 1


adaboost = AdaBoostClassifier(random_state=42)
adaboost.fit(X_train, y_train)

AdaBoostClassifier(random_state=42)

AdaBoostClassifier(random_state=42)


y_train_AdaBoost = adaboost.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train, y_train_AdaBoost)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_train, y_train_AdaBoost))

              precision    recall  f1-score   support

           0       0.92      0.90      0.91     47408
           1       0.90      0.92      0.91     47413

    accuracy                           0.91     94821
   macro avg       0.91      0.91      0.91     94821
weighted avg       0.91      0.91      0.91     94821


set_scores(results_train,"AdaBoost",y_train,y_train_AdaBoost)


y_test_AdaBoost = adaboost.predict(X_test)


lista_predizioni.append(y_test_AdaBoost)


confusion_matrix = metrics.confusion_matrix(y_test, y_test_AdaBoost)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

print(classification_report(y_test, y_test_AdaBoost))

              precision    recall  f1-score   support

           0       0.92      0.90      0.91     23354
           1       0.90      0.92      0.91     23349

    accuracy                           0.91     46703
   macro avg       0.91      0.91      0.91     46703
weighted avg       0.91      0.91      0.91     46703


set_scores(results_test,"AdaBoost",y_test,y_test_AdaBoost)


xgb = XGBClassifier(random_state=42, nthread=8)
xgb.fit(X_train,y_train)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, nthread=8, num_parallel_tree=None,
              predictor=None, ...)

XGBClassifier(base_score=None, booster=None, callbacks=None,
              colsample_bylevel=None, colsample_bynode=None,
              colsample_bytree=None, early_stopping_rounds=None,
              enable_categorical=False, eval_metric=None, feature_types=None,
              gamma=None, gpu_id=None, grow_policy=None, importance_type=None,
              interaction_constraints=None, learning_rate=None, max_bin=None,
              max_cat_threshold=None, max_cat_to_onehot=None,
              max_delta_step=None, max_depth=None, max_leaves=None,
              min_child_weight=None, missing=nan, monotone_constraints=None,
              n_estimators=100, n_jobs=None, nthread=8, num_parallel_tree=None,
              predictor=None, ...)


y_train_xgb = xgb.predict(X_train)


confusion_matrix = metrics.confusion_matrix(y_train, y_train_xgb)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix=confusion_matrix, display_labels=[0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')

plt.show()

print(classification_report(y_train, y_train_xgb))

              precision    recall  f1-score   support

           0       0.98      0.99      0.99     47408
           1       0.99      0.98      0.99     47413

    accuracy                           0.99     94821
   macro avg       0.99      0.99      0.99     94821
weighted avg       0.99      0.99      0.99     94821


set_scores(results_train,"XGBoost",y_train,y_train_xgb)


y_test_xgb = xgb.predict(X_test)


lista_predizioni.append(y_test_xgb)


confusion_matrix = metrics.confusion_matrix(y_test, y_test_xgb)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')

plt.show()

print(classification_report(y_test, y_test_xgb))

              precision    recall  f1-score   support

           0       0.97      0.98      0.97     23354
           1       0.98      0.97      0.97     23349

    accuracy                           0.97     46703
   macro avg       0.97      0.97      0.97     46703
weighted avg       0.97      0.97      0.97     46703


set_scores(results_test,"XGBoost",y_test,y_test_xgb)


results_train


results_test


data_frame = results_test.sort_values('accuracy', ascending=False)

plt.figure(figsize=(27,10))
plt.bar(data_frame.index, data_frame['accuracy'])
fig.show()
plt.ylabel('Accuracy',  fontsize=20)
plt.xlabel('Models',  fontsize=20)
ax = plt.title('Accuracy dei modelli',  fontsize=25)


data_frame = results_test.sort_values('precision', ascending=False)

plt.figure(figsize=(27,10))
plt.bar(data_frame.index, data_frame['precision'])
fig.show()
plt.ylabel('Precision',  fontsize=20)
plt.xlabel('Models',  fontsize=20)
ax = plt.title('Precision dei modelli',  fontsize=25)


data_frame = results_test.sort_values('recall', ascending=False)

plt.figure(figsize=(27,10))
plt.bar(data_frame.index, data_frame['recall'])
fig.show()
plt.ylabel('Recall',  fontsize=20)
plt.xlabel('Models',  fontsize=20)
ax = plt.title('Recall dei modelli',  fontsize=25)


data_frame = results_test.sort_values('f1', ascending=False)

plt.figure(figsize=(27,10))
plt.bar(data_frame.index, data_frame['f1'])
fig.show()
plt.ylabel('F1',  fontsize=20)
plt.xlabel('Models',  fontsize=20)
ax = plt.title('F1 score dei modelli',  fontsize=25)


image2 = 'rete_neurale.png'
Image(filename=os.path.join(image2),width=350)


df_neural_X = df_final.drop('RainTomorrow', axis=1)
df_neural_Y = df_final['RainTomorrow']


from keras.callbacks import EarlyStopping

#Splitting in train test, test set, validation set
X_train_rete, X_test_rete, y_train_rete, y_test_rete = train_test_split(df_neural_X, df_neural_Y, test_size=0.1, random_state=42)
X_train_val, X_val, y_train_val, y_val = train_test_split(X_train_rete, y_train_rete, test_size=0.22, random_state=42)

#Creazione dello scaler
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train_val)
X_val_scaled = scaler.transform(X_val)
X_test_scaled = scaler.transform(X_test_rete)

# Definisco l'early stopping
early_stopping = EarlyStopping(monitor='recall', patience=50, mode='max', verbose=1)

#Creazione del modello
model = Sequential()
model.add(Dense(32, activation='relu', input_shape=(X_train_scaled.shape[1],)))
model.add(Dense(64, activation='relu'))
model.add(Dense(128, activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(1, activation='sigmoid', kernel_initializer='normal'))

#Compilazione del modello
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=[tf.keras.metrics.Recall(), tf.keras.metrics.Precision(), tf.keras.metrics.BinaryAccuracy()])

#Addestramento del modello con validation
history = model.fit(X_train_scaled, y_train_val, validation_data=(X_val_scaled, y_val), epochs=350, batch_size=2048)

#valutazione sul test set
test_loss, test_recall, test_precision, test_balanced_accuracy = model.evaluate(X_test_scaled, y_test_rete, verbose=1, callbacks=[early_stopping])
print("Test recall: ", test_recall)

# Generate predictions on the test set
y_pred_probability = model.predict(X_test_scaled)
threshold = 0.5
y_pred = (y_pred_probability > threshold).astype("int32")

Epoch 1/350
49/49 [==============================] - 4s 26ms/step - loss: 0.4930 - recall: 0.8166 - precision: 0.8361 - binary_accuracy: 0.8285 - val_loss: 0.3163 - val_recall: 0.8971 - val_precision: 0.8345 - val_binary_accuracy: 0.8595
Epoch 2/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2952 - recall: 0.8899 - precision: 0.8577 - binary_accuracy: 0.8713 - val_loss: 0.2817 - val_recall: 0.9014 - val_precision: 0.8614 - val_binary_accuracy: 0.8781
Epoch 3/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2712 - recall: 0.9018 - precision: 0.8699 - binary_accuracy: 0.8836 - val_loss: 0.2633 - val_recall: 0.9165 - val_precision: 0.8703 - val_binary_accuracy: 0.8899
Epoch 4/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2521 - recall: 0.9132 - precision: 0.8839 - binary_accuracy: 0.8967 - val_loss: 0.2427 - val_recall: 0.9197 - val_precision: 0.8902 - val_binary_accuracy: 0.9031
Epoch 5/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2330 - recall: 0.9220 - precision: 0.8974 - binary_accuracy: 0.9084 - val_loss: 0.2268 - val_recall: 0.9235 - val_precision: 0.9042 - val_binary_accuracy: 0.9128
Epoch 6/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2165 - recall: 0.9272 - precision: 0.9093 - binary_accuracy: 0.9174 - val_loss: 0.2104 - val_recall: 0.9381 - val_precision: 0.9103 - val_binary_accuracy: 0.9228
Epoch 7/350
49/49 [==============================] - 1s 13ms/step - loss: 0.2018 - recall: 0.9338 - precision: 0.9166 - binary_accuracy: 0.9245 - val_loss: 0.1999 - val_recall: 0.9234 - val_precision: 0.9298 - val_binary_accuracy: 0.9268
Epoch 8/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1913 - recall: 0.9364 - precision: 0.9223 - binary_accuracy: 0.9289 - val_loss: 0.1901 - val_recall: 0.9284 - val_precision: 0.9319 - val_binary_accuracy: 0.9303
Epoch 9/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1845 - recall: 0.9375 - precision: 0.9256 - binary_accuracy: 0.9312 - val_loss: 0.1830 - val_recall: 0.9391 - val_precision: 0.9279 - val_binary_accuracy: 0.9331
Epoch 10/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1792 - recall: 0.9373 - precision: 0.9279 - binary_accuracy: 0.9323 - val_loss: 0.1779 - val_recall: 0.9272 - val_precision: 0.9397 - val_binary_accuracy: 0.9338
Epoch 11/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1723 - recall: 0.9404 - precision: 0.9309 - binary_accuracy: 0.9354 - val_loss: 0.1703 - val_recall: 0.9475 - val_precision: 0.9292 - val_binary_accuracy: 0.9376
Epoch 12/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1672 - recall: 0.9421 - precision: 0.9320 - binary_accuracy: 0.9368 - val_loss: 0.1669 - val_recall: 0.9511 - val_precision: 0.9277 - val_binary_accuracy: 0.9385
Epoch 13/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1630 - recall: 0.9440 - precision: 0.9342 - binary_accuracy: 0.9388 - val_loss: 0.1654 - val_recall: 0.9567 - val_precision: 0.9225 - val_binary_accuracy: 0.9381
Epoch 14/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1589 - recall: 0.9458 - precision: 0.9343 - binary_accuracy: 0.9397 - val_loss: 0.1600 - val_recall: 0.9443 - val_precision: 0.9376 - val_binary_accuracy: 0.9408
Epoch 15/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1562 - recall: 0.9471 - precision: 0.9355 - binary_accuracy: 0.9410 - val_loss: 0.1640 - val_recall: 0.9615 - val_precision: 0.9197 - val_binary_accuracy: 0.9388
Epoch 16/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1537 - recall: 0.9489 - precision: 0.9355 - binary_accuracy: 0.9418 - val_loss: 0.1552 - val_recall: 0.9620 - val_precision: 0.9269 - val_binary_accuracy: 0.9430
Epoch 17/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1504 - recall: 0.9488 - precision: 0.9365 - binary_accuracy: 0.9423 - val_loss: 0.1514 - val_recall: 0.9458 - val_precision: 0.9410 - val_binary_accuracy: 0.9433
Epoch 18/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1471 - recall: 0.9518 - precision: 0.9372 - binary_accuracy: 0.9441 - val_loss: 0.1491 - val_recall: 0.9584 - val_precision: 0.9330 - val_binary_accuracy: 0.9448
Epoch 19/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1450 - recall: 0.9524 - precision: 0.9379 - binary_accuracy: 0.9447 - val_loss: 0.1512 - val_recall: 0.9649 - val_precision: 0.9270 - val_binary_accuracy: 0.9444
Epoch 20/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1426 - recall: 0.9541 - precision: 0.9385 - binary_accuracy: 0.9458 - val_loss: 0.1458 - val_recall: 0.9565 - val_precision: 0.9365 - val_binary_accuracy: 0.9458
Epoch 21/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1405 - recall: 0.9540 - precision: 0.9393 - binary_accuracy: 0.9462 - val_loss: 0.1461 - val_recall: 0.9454 - val_precision: 0.9451 - val_binary_accuracy: 0.9453
Epoch 22/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1386 - recall: 0.9549 - precision: 0.9398 - binary_accuracy: 0.9469 - val_loss: 0.1434 - val_recall: 0.9538 - val_precision: 0.9401 - val_binary_accuracy: 0.9465
Epoch 23/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1362 - recall: 0.9557 - precision: 0.9410 - binary_accuracy: 0.9479 - val_loss: 0.1431 - val_recall: 0.9593 - val_precision: 0.9348 - val_binary_accuracy: 0.9461
Epoch 24/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1363 - recall: 0.9561 - precision: 0.9399 - binary_accuracy: 0.9475 - val_loss: 0.1469 - val_recall: 0.9686 - val_precision: 0.9254 - val_binary_accuracy: 0.9453
Epoch 25/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1340 - recall: 0.9581 - precision: 0.9404 - binary_accuracy: 0.9488 - val_loss: 0.1415 - val_recall: 0.9508 - val_precision: 0.9428 - val_binary_accuracy: 0.9466
Epoch 26/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1317 - recall: 0.9590 - precision: 0.9416 - binary_accuracy: 0.9498 - val_loss: 0.1494 - val_recall: 0.9328 - val_precision: 0.9513 - val_binary_accuracy: 0.9425
Epoch 27/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1312 - recall: 0.9591 - precision: 0.9417 - binary_accuracy: 0.9499 - val_loss: 0.1407 - val_recall: 0.9451 - val_precision: 0.9480 - val_binary_accuracy: 0.9466
Epoch 28/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1291 - recall: 0.9594 - precision: 0.9418 - binary_accuracy: 0.9501 - val_loss: 0.1363 - val_recall: 0.9629 - val_precision: 0.9384 - val_binary_accuracy: 0.9499
Epoch 29/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1272 - recall: 0.9600 - precision: 0.9430 - binary_accuracy: 0.9510 - val_loss: 0.1451 - val_recall: 0.9747 - val_precision: 0.9199 - val_binary_accuracy: 0.9449
Epoch 30/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1275 - recall: 0.9601 - precision: 0.9422 - binary_accuracy: 0.9506 - val_loss: 0.1371 - val_recall: 0.9706 - val_precision: 0.9317 - val_binary_accuracy: 0.9497
Epoch 31/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1257 - recall: 0.9615 - precision: 0.9424 - binary_accuracy: 0.9514 - val_loss: 0.1347 - val_recall: 0.9538 - val_precision: 0.9455 - val_binary_accuracy: 0.9494
Epoch 32/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1243 - recall: 0.9616 - precision: 0.9435 - binary_accuracy: 0.9521 - val_loss: 0.1342 - val_recall: 0.9590 - val_precision: 0.9412 - val_binary_accuracy: 0.9495
Epoch 33/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1233 - recall: 0.9628 - precision: 0.9437 - binary_accuracy: 0.9527 - val_loss: 0.1342 - val_recall: 0.9570 - val_precision: 0.9446 - val_binary_accuracy: 0.9504
Epoch 34/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1222 - recall: 0.9624 - precision: 0.9438 - binary_accuracy: 0.9526 - val_loss: 0.1326 - val_recall: 0.9629 - val_precision: 0.9405 - val_binary_accuracy: 0.9510
Epoch 35/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1219 - recall: 0.9641 - precision: 0.9444 - binary_accuracy: 0.9537 - val_loss: 0.1344 - val_recall: 0.9510 - val_precision: 0.9489 - val_binary_accuracy: 0.9499
Epoch 36/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1199 - recall: 0.9647 - precision: 0.9449 - binary_accuracy: 0.9543 - val_loss: 0.1314 - val_recall: 0.9643 - val_precision: 0.9391 - val_binary_accuracy: 0.9509
Epoch 37/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1188 - recall: 0.9647 - precision: 0.9456 - binary_accuracy: 0.9546 - val_loss: 0.1317 - val_recall: 0.9605 - val_precision: 0.9406 - val_binary_accuracy: 0.9499
Epoch 38/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1182 - recall: 0.9653 - precision: 0.9451 - binary_accuracy: 0.9546 - val_loss: 0.1302 - val_recall: 0.9605 - val_precision: 0.9430 - val_binary_accuracy: 0.9512
Epoch 39/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1171 - recall: 0.9648 - precision: 0.9454 - binary_accuracy: 0.9546 - val_loss: 0.1316 - val_recall: 0.9709 - val_precision: 0.9346 - val_binary_accuracy: 0.9515
Epoch 40/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1206 - recall: 0.9644 - precision: 0.9430 - binary_accuracy: 0.9531 - val_loss: 0.1300 - val_recall: 0.9643 - val_precision: 0.9415 - val_binary_accuracy: 0.9522
Epoch 41/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1185 - recall: 0.9649 - precision: 0.9441 - binary_accuracy: 0.9539 - val_loss: 0.1297 - val_recall: 0.9587 - val_precision: 0.9438 - val_binary_accuracy: 0.9508
Epoch 42/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1146 - recall: 0.9664 - precision: 0.9471 - binary_accuracy: 0.9563 - val_loss: 0.1283 - val_recall: 0.9660 - val_precision: 0.9397 - val_binary_accuracy: 0.9520
Epoch 43/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1136 - recall: 0.9673 - precision: 0.9466 - binary_accuracy: 0.9564 - val_loss: 0.1282 - val_recall: 0.9624 - val_precision: 0.9433 - val_binary_accuracy: 0.9523
Epoch 44/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1133 - recall: 0.9674 - precision: 0.9472 - binary_accuracy: 0.9567 - val_loss: 0.1277 - val_recall: 0.9677 - val_precision: 0.9382 - val_binary_accuracy: 0.9520
Epoch 45/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1123 - recall: 0.9674 - precision: 0.9474 - binary_accuracy: 0.9569 - val_loss: 0.1327 - val_recall: 0.9766 - val_precision: 0.9281 - val_binary_accuracy: 0.9505
Epoch 46/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1118 - recall: 0.9679 - precision: 0.9474 - binary_accuracy: 0.9571 - val_loss: 0.1265 - val_recall: 0.9597 - val_precision: 0.9464 - val_binary_accuracy: 0.9526
Epoch 47/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1117 - recall: 0.9672 - precision: 0.9478 - binary_accuracy: 0.9570 - val_loss: 0.1281 - val_recall: 0.9718 - val_precision: 0.9349 - val_binary_accuracy: 0.9521
Epoch 48/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1112 - recall: 0.9691 - precision: 0.9468 - binary_accuracy: 0.9574 - val_loss: 0.1279 - val_recall: 0.9659 - val_precision: 0.9408 - val_binary_accuracy: 0.9526
Epoch 49/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1103 - recall: 0.9686 - precision: 0.9482 - binary_accuracy: 0.9579 - val_loss: 0.1276 - val_recall: 0.9599 - val_precision: 0.9455 - val_binary_accuracy: 0.9523
Epoch 50/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1086 - recall: 0.9697 - precision: 0.9482 - binary_accuracy: 0.9584 - val_loss: 0.1246 - val_recall: 0.9627 - val_precision: 0.9450 - val_binary_accuracy: 0.9534
Epoch 51/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1089 - recall: 0.9695 - precision: 0.9486 - binary_accuracy: 0.9585 - val_loss: 0.1282 - val_recall: 0.9589 - val_precision: 0.9450 - val_binary_accuracy: 0.9515
Epoch 52/350
49/49 [==============================] - 1s 12ms/step - loss: 0.1095 - recall: 0.9687 - precision: 0.9476 - binary_accuracy: 0.9576 - val_loss: 0.1267 - val_recall: 0.9680 - val_precision: 0.9390 - val_binary_accuracy: 0.9526
Epoch 53/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1072 - recall: 0.9704 - precision: 0.9488 - binary_accuracy: 0.9591 - val_loss: 0.1258 - val_recall: 0.9648 - val_precision: 0.9432 - val_binary_accuracy: 0.9534
Epoch 54/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1066 - recall: 0.9710 - precision: 0.9493 - binary_accuracy: 0.9596 - val_loss: 0.1264 - val_recall: 0.9640 - val_precision: 0.9437 - val_binary_accuracy: 0.9533
Epoch 55/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1072 - recall: 0.9695 - precision: 0.9485 - binary_accuracy: 0.9585 - val_loss: 0.1316 - val_recall: 0.9463 - val_precision: 0.9536 - val_binary_accuracy: 0.9501
Epoch 56/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1072 - recall: 0.9700 - precision: 0.9492 - binary_accuracy: 0.9591 - val_loss: 0.1240 - val_recall: 0.9665 - val_precision: 0.9417 - val_binary_accuracy: 0.9533
Epoch 57/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1046 - recall: 0.9710 - precision: 0.9500 - binary_accuracy: 0.9600 - val_loss: 0.1251 - val_recall: 0.9712 - val_precision: 0.9380 - val_binary_accuracy: 0.9535
Epoch 58/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1059 - recall: 0.9707 - precision: 0.9498 - binary_accuracy: 0.9597 - val_loss: 0.1236 - val_recall: 0.9665 - val_precision: 0.9442 - val_binary_accuracy: 0.9547
Epoch 59/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1047 - recall: 0.9717 - precision: 0.9503 - binary_accuracy: 0.9605 - val_loss: 0.1292 - val_recall: 0.9739 - val_precision: 0.9316 - val_binary_accuracy: 0.9512
Epoch 60/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1050 - recall: 0.9712 - precision: 0.9496 - binary_accuracy: 0.9599 - val_loss: 0.1240 - val_recall: 0.9598 - val_precision: 0.9500 - val_binary_accuracy: 0.9546
Epoch 61/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1046 - recall: 0.9714 - precision: 0.9498 - binary_accuracy: 0.9601 - val_loss: 0.1239 - val_recall: 0.9655 - val_precision: 0.9440 - val_binary_accuracy: 0.9541
Epoch 62/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1034 - recall: 0.9722 - precision: 0.9504 - binary_accuracy: 0.9608 - val_loss: 0.1234 - val_recall: 0.9683 - val_precision: 0.9422 - val_binary_accuracy: 0.9544
Epoch 63/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1028 - recall: 0.9722 - precision: 0.9503 - binary_accuracy: 0.9607 - val_loss: 0.1233 - val_recall: 0.9662 - val_precision: 0.9454 - val_binary_accuracy: 0.9552
Epoch 64/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1013 - recall: 0.9729 - precision: 0.9509 - binary_accuracy: 0.9613 - val_loss: 0.1226 - val_recall: 0.9708 - val_precision: 0.9413 - val_binary_accuracy: 0.9551
Epoch 65/350
49/49 [==============================] - 1s 14ms/step - loss: 0.1038 - recall: 0.9719 - precision: 0.9501 - binary_accuracy: 0.9604 - val_loss: 0.1274 - val_recall: 0.9598 - val_precision: 0.9459 - val_binary_accuracy: 0.9524
Epoch 66/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1015 - recall: 0.9732 - precision: 0.9512 - binary_accuracy: 0.9617 - val_loss: 0.1245 - val_recall: 0.9690 - val_precision: 0.9406 - val_binary_accuracy: 0.9539
Epoch 67/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1009 - recall: 0.9726 - precision: 0.9512 - binary_accuracy: 0.9614 - val_loss: 0.1245 - val_recall: 0.9541 - val_precision: 0.9516 - val_binary_accuracy: 0.9528
Epoch 68/350
49/49 [==============================] - 1s 13ms/step - loss: 0.1004 - recall: 0.9730 - precision: 0.9514 - binary_accuracy: 0.9617 - val_loss: 0.1264 - val_recall: 0.9772 - val_precision: 0.9339 - val_binary_accuracy: 0.9540
Epoch 69/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0995 - recall: 0.9735 - precision: 0.9523 - binary_accuracy: 0.9624 - val_loss: 0.1236 - val_recall: 0.9675 - val_precision: 0.9440 - val_binary_accuracy: 0.9551
Epoch 70/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0983 - recall: 0.9743 - precision: 0.9532 - binary_accuracy: 0.9633 - val_loss: 0.1234 - val_recall: 0.9720 - val_precision: 0.9396 - val_binary_accuracy: 0.9548
Epoch 71/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0983 - recall: 0.9737 - precision: 0.9528 - binary_accuracy: 0.9628 - val_loss: 0.1370 - val_recall: 0.9851 - val_precision: 0.9224 - val_binary_accuracy: 0.9511
Epoch 72/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0996 - recall: 0.9729 - precision: 0.9514 - binary_accuracy: 0.9616 - val_loss: 0.1247 - val_recall: 0.9566 - val_precision: 0.9512 - val_binary_accuracy: 0.9538
Epoch 73/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0999 - recall: 0.9732 - precision: 0.9526 - binary_accuracy: 0.9624 - val_loss: 0.1227 - val_recall: 0.9687 - val_precision: 0.9426 - val_binary_accuracy: 0.9549
Epoch 74/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0984 - recall: 0.9747 - precision: 0.9516 - binary_accuracy: 0.9626 - val_loss: 0.1234 - val_recall: 0.9751 - val_precision: 0.9376 - val_binary_accuracy: 0.9551
Epoch 75/350
49/49 [==============================] - 1s 12ms/step - loss: 0.0970 - recall: 0.9743 - precision: 0.9527 - binary_accuracy: 0.9630 - val_loss: 0.1215 - val_recall: 0.9718 - val_precision: 0.9424 - val_binary_accuracy: 0.9562
Epoch 76/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0982 - recall: 0.9745 - precision: 0.9520 - binary_accuracy: 0.9628 - val_loss: 0.1258 - val_recall: 0.9481 - val_precision: 0.9571 - val_binary_accuracy: 0.9528
Epoch 77/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0973 - recall: 0.9737 - precision: 0.9532 - binary_accuracy: 0.9630 - val_loss: 0.1218 - val_recall: 0.9693 - val_precision: 0.9454 - val_binary_accuracy: 0.9566
Epoch 78/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0957 - recall: 0.9752 - precision: 0.9539 - binary_accuracy: 0.9641 - val_loss: 0.1232 - val_recall: 0.9595 - val_precision: 0.9500 - val_binary_accuracy: 0.9545
Epoch 79/350
49/49 [==============================] - 1s 12ms/step - loss: 0.0955 - recall: 0.9755 - precision: 0.9540 - binary_accuracy: 0.9643 - val_loss: 0.1213 - val_recall: 0.9733 - val_precision: 0.9419 - val_binary_accuracy: 0.9566
Epoch 80/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0944 - recall: 0.9773 - precision: 0.9534 - binary_accuracy: 0.9648 - val_loss: 0.1237 - val_recall: 0.9542 - val_precision: 0.9539 - val_binary_accuracy: 0.9540
Epoch 81/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0959 - recall: 0.9753 - precision: 0.9534 - binary_accuracy: 0.9639 - val_loss: 0.1268 - val_recall: 0.9822 - val_precision: 0.9313 - val_binary_accuracy: 0.9548
Epoch 82/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0948 - recall: 0.9758 - precision: 0.9536 - binary_accuracy: 0.9642 - val_loss: 0.1195 - val_recall: 0.9717 - val_precision: 0.9450 - val_binary_accuracy: 0.9576
Epoch 83/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0935 - recall: 0.9763 - precision: 0.9547 - binary_accuracy: 0.9650 - val_loss: 0.1299 - val_recall: 0.9432 - val_precision: 0.9577 - val_binary_accuracy: 0.9508
Epoch 84/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0948 - recall: 0.9750 - precision: 0.9538 - binary_accuracy: 0.9639 - val_loss: 0.1210 - val_recall: 0.9722 - val_precision: 0.9431 - val_binary_accuracy: 0.9568
Epoch 85/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0931 - recall: 0.9772 - precision: 0.9537 - binary_accuracy: 0.9649 - val_loss: 0.1214 - val_recall: 0.9708 - val_precision: 0.9428 - val_binary_accuracy: 0.9559
Epoch 86/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0925 - recall: 0.9769 - precision: 0.9552 - binary_accuracy: 0.9656 - val_loss: 0.1227 - val_recall: 0.9732 - val_precision: 0.9409 - val_binary_accuracy: 0.9560
Epoch 87/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0943 - recall: 0.9756 - precision: 0.9543 - binary_accuracy: 0.9645 - val_loss: 0.1193 - val_recall: 0.9721 - val_precision: 0.9435 - val_binary_accuracy: 0.9569
Epoch 88/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0920 - recall: 0.9769 - precision: 0.9551 - binary_accuracy: 0.9655 - val_loss: 0.1212 - val_recall: 0.9646 - val_precision: 0.9488 - val_binary_accuracy: 0.9562
Epoch 89/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0933 - recall: 0.9766 - precision: 0.9543 - binary_accuracy: 0.9650 - val_loss: 0.1207 - val_recall: 0.9734 - val_precision: 0.9428 - val_binary_accuracy: 0.9571
Epoch 90/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0916 - recall: 0.9772 - precision: 0.9554 - binary_accuracy: 0.9658 - val_loss: 0.1252 - val_recall: 0.9768 - val_precision: 0.9386 - val_binary_accuracy: 0.9564
Epoch 91/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0934 - recall: 0.9760 - precision: 0.9546 - binary_accuracy: 0.9648 - val_loss: 0.1235 - val_recall: 0.9754 - val_precision: 0.9363 - val_binary_accuracy: 0.9545
Epoch 92/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0923 - recall: 0.9773 - precision: 0.9549 - binary_accuracy: 0.9656 - val_loss: 0.1199 - val_recall: 0.9755 - val_precision: 0.9405 - val_binary_accuracy: 0.9569
Epoch 93/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0904 - recall: 0.9774 - precision: 0.9559 - binary_accuracy: 0.9662 - val_loss: 0.1220 - val_recall: 0.9757 - val_precision: 0.9376 - val_binary_accuracy: 0.9554
Epoch 94/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0901 - recall: 0.9774 - precision: 0.9553 - binary_accuracy: 0.9659 - val_loss: 0.1185 - val_recall: 0.9713 - val_precision: 0.9470 - val_binary_accuracy: 0.9585
Epoch 95/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0891 - recall: 0.9779 - precision: 0.9562 - binary_accuracy: 0.9666 - val_loss: 0.1214 - val_recall: 0.9642 - val_precision: 0.9491 - val_binary_accuracy: 0.9562
Epoch 96/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0884 - recall: 0.9786 - precision: 0.9572 - binary_accuracy: 0.9675 - val_loss: 0.1230 - val_recall: 0.9620 - val_precision: 0.9504 - val_binary_accuracy: 0.9559
Epoch 97/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0904 - recall: 0.9774 - precision: 0.9556 - binary_accuracy: 0.9660 - val_loss: 0.1222 - val_recall: 0.9791 - val_precision: 0.9376 - val_binary_accuracy: 0.9570
Epoch 98/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0894 - recall: 0.9778 - precision: 0.9563 - binary_accuracy: 0.9666 - val_loss: 0.1178 - val_recall: 0.9707 - val_precision: 0.9458 - val_binary_accuracy: 0.9576
Epoch 99/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0877 - recall: 0.9786 - precision: 0.9565 - binary_accuracy: 0.9671 - val_loss: 0.1216 - val_recall: 0.9668 - val_precision: 0.9485 - val_binary_accuracy: 0.9571
Epoch 100/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0886 - recall: 0.9783 - precision: 0.9563 - binary_accuracy: 0.9668 - val_loss: 0.1228 - val_recall: 0.9571 - val_precision: 0.9536 - val_binary_accuracy: 0.9553
Epoch 101/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0886 - recall: 0.9780 - precision: 0.9568 - binary_accuracy: 0.9669 - val_loss: 0.1196 - val_recall: 0.9648 - val_precision: 0.9498 - val_binary_accuracy: 0.9569
Epoch 102/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0869 - recall: 0.9792 - precision: 0.9573 - binary_accuracy: 0.9678 - val_loss: 0.1217 - val_recall: 0.9794 - val_precision: 0.9359 - val_binary_accuracy: 0.9562
Epoch 103/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0877 - recall: 0.9779 - precision: 0.9568 - binary_accuracy: 0.9669 - val_loss: 0.1191 - val_recall: 0.9660 - val_precision: 0.9508 - val_binary_accuracy: 0.9580
Epoch 104/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0873 - recall: 0.9785 - precision: 0.9572 - binary_accuracy: 0.9674 - val_loss: 0.1215 - val_recall: 0.9737 - val_precision: 0.9410 - val_binary_accuracy: 0.9564
Epoch 105/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0861 - recall: 0.9797 - precision: 0.9576 - binary_accuracy: 0.9682 - val_loss: 0.1196 - val_recall: 0.9647 - val_precision: 0.9501 - val_binary_accuracy: 0.9570
Epoch 106/350
49/49 [==============================] - 1s 19ms/step - loss: 0.0869 - recall: 0.9788 - precision: 0.9579 - binary_accuracy: 0.9679 - val_loss: 0.1194 - val_recall: 0.9760 - val_precision: 0.9422 - val_binary_accuracy: 0.9581
Epoch 107/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0868 - recall: 0.9785 - precision: 0.9577 - binary_accuracy: 0.9677 - val_loss: 0.1184 - val_recall: 0.9662 - val_precision: 0.9502 - val_binary_accuracy: 0.9578
Epoch 108/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0857 - recall: 0.9787 - precision: 0.9576 - binary_accuracy: 0.9678 - val_loss: 0.1217 - val_recall: 0.9670 - val_precision: 0.9478 - val_binary_accuracy: 0.9569
Epoch 109/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0844 - recall: 0.9795 - precision: 0.9588 - binary_accuracy: 0.9688 - val_loss: 0.1205 - val_recall: 0.9762 - val_precision: 0.9417 - val_binary_accuracy: 0.9579
Epoch 110/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0865 - recall: 0.9791 - precision: 0.9577 - binary_accuracy: 0.9680 - val_loss: 0.1203 - val_recall: 0.9695 - val_precision: 0.9444 - val_binary_accuracy: 0.9562
Epoch 111/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0849 - recall: 0.9793 - precision: 0.9588 - binary_accuracy: 0.9686 - val_loss: 0.1196 - val_recall: 0.9720 - val_precision: 0.9445 - val_binary_accuracy: 0.9575
Epoch 112/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0855 - recall: 0.9792 - precision: 0.9585 - binary_accuracy: 0.9684 - val_loss: 0.1245 - val_recall: 0.9684 - val_precision: 0.9425 - val_binary_accuracy: 0.9546
Epoch 113/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0850 - recall: 0.9794 - precision: 0.9591 - binary_accuracy: 0.9688 - val_loss: 0.1175 - val_recall: 0.9692 - val_precision: 0.9493 - val_binary_accuracy: 0.9587
Epoch 114/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0829 - recall: 0.9806 - precision: 0.9593 - binary_accuracy: 0.9695 - val_loss: 0.1204 - val_recall: 0.9677 - val_precision: 0.9490 - val_binary_accuracy: 0.9579
Epoch 115/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0831 - recall: 0.9799 - precision: 0.9589 - binary_accuracy: 0.9690 - val_loss: 0.1325 - val_recall: 0.9384 - val_precision: 0.9605 - val_binary_accuracy: 0.9499
Epoch 116/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0842 - recall: 0.9792 - precision: 0.9589 - binary_accuracy: 0.9687 - val_loss: 0.1209 - val_recall: 0.9640 - val_precision: 0.9511 - val_binary_accuracy: 0.9572
Epoch 117/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0826 - recall: 0.9803 - precision: 0.9597 - binary_accuracy: 0.9696 - val_loss: 0.1220 - val_recall: 0.9666 - val_precision: 0.9481 - val_binary_accuracy: 0.9568
Epoch 118/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0852 - recall: 0.9792 - precision: 0.9583 - binary_accuracy: 0.9683 - val_loss: 0.1201 - val_recall: 0.9800 - val_precision: 0.9405 - val_binary_accuracy: 0.9590
Epoch 119/350
49/49 [==============================] - 1s 22ms/step - loss: 0.0829 - recall: 0.9804 - precision: 0.9592 - binary_accuracy: 0.9694 - val_loss: 0.1220 - val_recall: 0.9752 - val_precision: 0.9429 - val_binary_accuracy: 0.9581
Epoch 120/350
49/49 [==============================] - 1s 19ms/step - loss: 0.0822 - recall: 0.9806 - precision: 0.9596 - binary_accuracy: 0.9697 - val_loss: 0.1177 - val_recall: 0.9720 - val_precision: 0.9482 - val_binary_accuracy: 0.9594
Epoch 121/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0828 - recall: 0.9805 - precision: 0.9590 - binary_accuracy: 0.9693 - val_loss: 0.1253 - val_recall: 0.9500 - val_precision: 0.9576 - val_binary_accuracy: 0.9540
Epoch 122/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0816 - recall: 0.9802 - precision: 0.9600 - binary_accuracy: 0.9697 - val_loss: 0.1266 - val_recall: 0.9705 - val_precision: 0.9440 - val_binary_accuracy: 0.9564
Epoch 123/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0807 - recall: 0.9813 - precision: 0.9608 - binary_accuracy: 0.9706 - val_loss: 0.1201 - val_recall: 0.9715 - val_precision: 0.9448 - val_binary_accuracy: 0.9574
Epoch 124/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0824 - recall: 0.9803 - precision: 0.9602 - binary_accuracy: 0.9699 - val_loss: 0.1199 - val_recall: 0.9757 - val_precision: 0.9426 - val_binary_accuracy: 0.9581
Epoch 125/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0810 - recall: 0.9814 - precision: 0.9597 - binary_accuracy: 0.9701 - val_loss: 0.1223 - val_recall: 0.9752 - val_precision: 0.9433 - val_binary_accuracy: 0.9583
Epoch 126/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0794 - recall: 0.9821 - precision: 0.9613 - binary_accuracy: 0.9713 - val_loss: 0.1197 - val_recall: 0.9766 - val_precision: 0.9429 - val_binary_accuracy: 0.9587
Epoch 127/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0809 - recall: 0.9810 - precision: 0.9602 - binary_accuracy: 0.9702 - val_loss: 0.1225 - val_recall: 0.9745 - val_precision: 0.9424 - val_binary_accuracy: 0.9574
Epoch 128/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0807 - recall: 0.9809 - precision: 0.9603 - binary_accuracy: 0.9702 - val_loss: 0.1179 - val_recall: 0.9670 - val_precision: 0.9501 - val_binary_accuracy: 0.9581
Epoch 129/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0802 - recall: 0.9806 - precision: 0.9605 - binary_accuracy: 0.9702 - val_loss: 0.1187 - val_recall: 0.9702 - val_precision: 0.9482 - val_binary_accuracy: 0.9586
Epoch 130/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0813 - recall: 0.9805 - precision: 0.9601 - binary_accuracy: 0.9699 - val_loss: 0.1177 - val_recall: 0.9713 - val_precision: 0.9483 - val_binary_accuracy: 0.9592
Epoch 131/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0781 - recall: 0.9826 - precision: 0.9612 - binary_accuracy: 0.9715 - val_loss: 0.1213 - val_recall: 0.9695 - val_precision: 0.9474 - val_binary_accuracy: 0.9578
Epoch 132/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0779 - recall: 0.9816 - precision: 0.9618 - binary_accuracy: 0.9714 - val_loss: 0.1213 - val_recall: 0.9622 - val_precision: 0.9519 - val_binary_accuracy: 0.9567
Epoch 133/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0800 - recall: 0.9816 - precision: 0.9609 - binary_accuracy: 0.9709 - val_loss: 0.1201 - val_recall: 0.9629 - val_precision: 0.9518 - val_binary_accuracy: 0.9570
Epoch 134/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0787 - recall: 0.9819 - precision: 0.9614 - binary_accuracy: 0.9713 - val_loss: 0.1196 - val_recall: 0.9718 - val_precision: 0.9495 - val_binary_accuracy: 0.9600
Epoch 135/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0787 - recall: 0.9822 - precision: 0.9619 - binary_accuracy: 0.9717 - val_loss: 0.1222 - val_recall: 0.9662 - val_precision: 0.9510 - val_binary_accuracy: 0.9582
Epoch 136/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0769 - recall: 0.9825 - precision: 0.9621 - binary_accuracy: 0.9719 - val_loss: 0.1230 - val_recall: 0.9585 - val_precision: 0.9532 - val_binary_accuracy: 0.9557
Epoch 137/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0777 - recall: 0.9818 - precision: 0.9619 - binary_accuracy: 0.9715 - val_loss: 0.1186 - val_recall: 0.9772 - val_precision: 0.9444 - val_binary_accuracy: 0.9599
Epoch 138/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0779 - recall: 0.9820 - precision: 0.9613 - binary_accuracy: 0.9713 - val_loss: 0.1205 - val_recall: 0.9747 - val_precision: 0.9442 - val_binary_accuracy: 0.9585
Epoch 139/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0771 - recall: 0.9824 - precision: 0.9620 - binary_accuracy: 0.9718 - val_loss: 0.1200 - val_recall: 0.9700 - val_precision: 0.9483 - val_binary_accuracy: 0.9585
Epoch 140/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0757 - recall: 0.9830 - precision: 0.9625 - binary_accuracy: 0.9724 - val_loss: 0.1305 - val_recall: 0.9465 - val_precision: 0.9580 - val_binary_accuracy: 0.9525
Epoch 141/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0777 - recall: 0.9816 - precision: 0.9622 - binary_accuracy: 0.9716 - val_loss: 0.1208 - val_recall: 0.9795 - val_precision: 0.9427 - val_binary_accuracy: 0.9600
Epoch 142/350
49/49 [==============================] - 1s 18ms/step - loss: 0.0751 - recall: 0.9832 - precision: 0.9625 - binary_accuracy: 0.9725 - val_loss: 0.1218 - val_recall: 0.9812 - val_precision: 0.9403 - val_binary_accuracy: 0.9594
Epoch 143/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0756 - recall: 0.9829 - precision: 0.9622 - binary_accuracy: 0.9722 - val_loss: 0.1248 - val_recall: 0.9568 - val_precision: 0.9565 - val_binary_accuracy: 0.9566
Epoch 144/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0764 - recall: 0.9822 - precision: 0.9623 - binary_accuracy: 0.9719 - val_loss: 0.1210 - val_recall: 0.9657 - val_precision: 0.9522 - val_binary_accuracy: 0.9586
Epoch 145/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0773 - recall: 0.9817 - precision: 0.9630 - binary_accuracy: 0.9720 - val_loss: 0.1215 - val_recall: 0.9756 - val_precision: 0.9450 - val_binary_accuracy: 0.9594
Epoch 146/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0741 - recall: 0.9835 - precision: 0.9639 - binary_accuracy: 0.9734 - val_loss: 0.1202 - val_recall: 0.9792 - val_precision: 0.9445 - val_binary_accuracy: 0.9608
Epoch 147/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0747 - recall: 0.9832 - precision: 0.9638 - binary_accuracy: 0.9731 - val_loss: 0.1228 - val_recall: 0.9695 - val_precision: 0.9464 - val_binary_accuracy: 0.9573
Epoch 148/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0731 - recall: 0.9841 - precision: 0.9639 - binary_accuracy: 0.9736 - val_loss: 0.1237 - val_recall: 0.9680 - val_precision: 0.9500 - val_binary_accuracy: 0.9585
Epoch 149/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0775 - recall: 0.9814 - precision: 0.9621 - binary_accuracy: 0.9714 - val_loss: 0.1196 - val_recall: 0.9699 - val_precision: 0.9496 - val_binary_accuracy: 0.9592
Epoch 150/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0758 - recall: 0.9829 - precision: 0.9630 - binary_accuracy: 0.9726 - val_loss: 0.1212 - val_recall: 0.9610 - val_precision: 0.9550 - val_binary_accuracy: 0.9579
Epoch 151/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0838 - recall: 0.9783 - precision: 0.9588 - binary_accuracy: 0.9682 - val_loss: 0.1265 - val_recall: 0.9513 - val_precision: 0.9592 - val_binary_accuracy: 0.9554
Epoch 152/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0743 - recall: 0.9833 - precision: 0.9640 - binary_accuracy: 0.9733 - val_loss: 0.1206 - val_recall: 0.9801 - val_precision: 0.9426 - val_binary_accuracy: 0.9602
Epoch 153/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0735 - recall: 0.9835 - precision: 0.9639 - binary_accuracy: 0.9733 - val_loss: 0.1208 - val_recall: 0.9766 - val_precision: 0.9439 - val_binary_accuracy: 0.9592
Epoch 154/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0730 - recall: 0.9839 - precision: 0.9647 - binary_accuracy: 0.9740 - val_loss: 0.1210 - val_recall: 0.9819 - val_precision: 0.9427 - val_binary_accuracy: 0.9611
Epoch 155/350
49/49 [==============================] - 1s 21ms/step - loss: 0.0723 - recall: 0.9845 - precision: 0.9643 - binary_accuracy: 0.9741 - val_loss: 0.1191 - val_recall: 0.9690 - val_precision: 0.9520 - val_binary_accuracy: 0.9601
Epoch 156/350
49/49 [==============================] - 1s 22ms/step - loss: 0.0716 - recall: 0.9842 - precision: 0.9654 - binary_accuracy: 0.9745 - val_loss: 0.1215 - val_recall: 0.9830 - val_precision: 0.9423 - val_binary_accuracy: 0.9614
Epoch 157/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0722 - recall: 0.9838 - precision: 0.9641 - binary_accuracy: 0.9736 - val_loss: 0.1244 - val_recall: 0.9575 - val_precision: 0.9558 - val_binary_accuracy: 0.9566
Epoch 158/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0739 - recall: 0.9829 - precision: 0.9639 - binary_accuracy: 0.9731 - val_loss: 0.1227 - val_recall: 0.9734 - val_precision: 0.9463 - val_binary_accuracy: 0.9591
Epoch 159/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0719 - recall: 0.9846 - precision: 0.9651 - binary_accuracy: 0.9745 - val_loss: 0.1192 - val_recall: 0.9747 - val_precision: 0.9491 - val_binary_accuracy: 0.9612
Epoch 160/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0751 - recall: 0.9824 - precision: 0.9626 - binary_accuracy: 0.9721 - val_loss: 0.1213 - val_recall: 0.9677 - val_precision: 0.9516 - val_binary_accuracy: 0.9592
Epoch 161/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0713 - recall: 0.9850 - precision: 0.9649 - binary_accuracy: 0.9746 - val_loss: 0.1199 - val_recall: 0.9632 - val_precision: 0.9556 - val_binary_accuracy: 0.9592
Epoch 162/350
49/49 [==============================] - 1s 19ms/step - loss: 0.0741 - recall: 0.9833 - precision: 0.9640 - binary_accuracy: 0.9733 - val_loss: 0.1190 - val_recall: 0.9675 - val_precision: 0.9529 - val_binary_accuracy: 0.9598
Epoch 163/350
49/49 [==============================] - 1s 23ms/step - loss: 0.0734 - recall: 0.9832 - precision: 0.9635 - binary_accuracy: 0.9730 - val_loss: 0.1202 - val_recall: 0.9647 - val_precision: 0.9545 - val_binary_accuracy: 0.9593
Epoch 164/350
49/49 [==============================] - 1s 25ms/step - loss: 0.0700 - recall: 0.9851 - precision: 0.9654 - binary_accuracy: 0.9749 - val_loss: 0.1234 - val_recall: 0.9715 - val_precision: 0.9468 - val_binary_accuracy: 0.9585
Epoch 165/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0737 - recall: 0.9832 - precision: 0.9636 - binary_accuracy: 0.9730 - val_loss: 0.1306 - val_recall: 0.9473 - val_precision: 0.9614 - val_binary_accuracy: 0.9546
Epoch 166/350
49/49 [==============================] - 1s 21ms/step - loss: 0.0739 - recall: 0.9833 - precision: 0.9637 - binary_accuracy: 0.9732 - val_loss: 0.1215 - val_recall: 0.9807 - val_precision: 0.9405 - val_binary_accuracy: 0.9593
Epoch 167/350
49/49 [==============================] - 1s 18ms/step - loss: 0.0701 - recall: 0.9849 - precision: 0.9656 - binary_accuracy: 0.9749 - val_loss: 0.1250 - val_recall: 0.9563 - val_precision: 0.9562 - val_binary_accuracy: 0.9562
Epoch 168/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0710 - recall: 0.9849 - precision: 0.9651 - binary_accuracy: 0.9747 - val_loss: 0.1227 - val_recall: 0.9587 - val_precision: 0.9583 - val_binary_accuracy: 0.9585
Epoch 169/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0701 - recall: 0.9849 - precision: 0.9659 - binary_accuracy: 0.9751 - val_loss: 0.1196 - val_recall: 0.9746 - val_precision: 0.9485 - val_binary_accuracy: 0.9609
Epoch 170/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0685 - recall: 0.9856 - precision: 0.9664 - binary_accuracy: 0.9757 - val_loss: 0.1216 - val_recall: 0.9645 - val_precision: 0.9546 - val_binary_accuracy: 0.9593
Epoch 171/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0709 - recall: 0.9841 - precision: 0.9654 - binary_accuracy: 0.9744 - val_loss: 0.1215 - val_recall: 0.9699 - val_precision: 0.9523 - val_binary_accuracy: 0.9606
Epoch 172/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0683 - recall: 0.9854 - precision: 0.9666 - binary_accuracy: 0.9757 - val_loss: 0.1263 - val_recall: 0.9794 - val_precision: 0.9440 - val_binary_accuracy: 0.9606
Epoch 173/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0723 - recall: 0.9831 - precision: 0.9645 - binary_accuracy: 0.9735 - val_loss: 0.1208 - val_recall: 0.9750 - val_precision: 0.9488 - val_binary_accuracy: 0.9612
Epoch 174/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0694 - recall: 0.9840 - precision: 0.9658 - binary_accuracy: 0.9746 - val_loss: 0.1196 - val_recall: 0.9706 - val_precision: 0.9519 - val_binary_accuracy: 0.9607
Epoch 175/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0681 - recall: 0.9855 - precision: 0.9668 - binary_accuracy: 0.9758 - val_loss: 0.1207 - val_recall: 0.9691 - val_precision: 0.9530 - val_binary_accuracy: 0.9606
Epoch 176/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0693 - recall: 0.9853 - precision: 0.9657 - binary_accuracy: 0.9751 - val_loss: 0.1322 - val_recall: 0.9446 - val_precision: 0.9610 - val_binary_accuracy: 0.9531
Epoch 177/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0699 - recall: 0.9844 - precision: 0.9659 - binary_accuracy: 0.9749 - val_loss: 0.1235 - val_recall: 0.9798 - val_precision: 0.9437 - val_binary_accuracy: 0.9607
Epoch 178/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0684 - recall: 0.9848 - precision: 0.9668 - binary_accuracy: 0.9755 - val_loss: 0.1205 - val_recall: 0.9737 - val_precision: 0.9503 - val_binary_accuracy: 0.9614
Epoch 179/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0688 - recall: 0.9848 - precision: 0.9662 - binary_accuracy: 0.9752 - val_loss: 0.1218 - val_recall: 0.9640 - val_precision: 0.9566 - val_binary_accuracy: 0.9601
Epoch 180/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0684 - recall: 0.9840 - precision: 0.9665 - binary_accuracy: 0.9750 - val_loss: 0.1207 - val_recall: 0.9755 - val_precision: 0.9486 - val_binary_accuracy: 0.9613
Epoch 181/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0690 - recall: 0.9852 - precision: 0.9660 - binary_accuracy: 0.9753 - val_loss: 0.1239 - val_recall: 0.9638 - val_precision: 0.9550 - val_binary_accuracy: 0.9592
Epoch 182/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0690 - recall: 0.9846 - precision: 0.9659 - binary_accuracy: 0.9749 - val_loss: 0.1195 - val_recall: 0.9711 - val_precision: 0.9512 - val_binary_accuracy: 0.9606
Epoch 183/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0669 - recall: 0.9853 - precision: 0.9671 - binary_accuracy: 0.9759 - val_loss: 0.1284 - val_recall: 0.9844 - val_precision: 0.9414 - val_binary_accuracy: 0.9616
Epoch 184/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0668 - recall: 0.9857 - precision: 0.9675 - binary_accuracy: 0.9763 - val_loss: 0.1243 - val_recall: 0.9817 - val_precision: 0.9426 - val_binary_accuracy: 0.9609
Epoch 185/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0664 - recall: 0.9860 - precision: 0.9677 - binary_accuracy: 0.9766 - val_loss: 0.1239 - val_recall: 0.9793 - val_precision: 0.9442 - val_binary_accuracy: 0.9607
Epoch 186/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0694 - recall: 0.9839 - precision: 0.9669 - binary_accuracy: 0.9751 - val_loss: 0.1232 - val_recall: 0.9841 - val_precision: 0.9417 - val_binary_accuracy: 0.9616
Epoch 187/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0659 - recall: 0.9864 - precision: 0.9675 - binary_accuracy: 0.9766 - val_loss: 0.1209 - val_recall: 0.9718 - val_precision: 0.9530 - val_binary_accuracy: 0.9619
Epoch 188/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0698 - recall: 0.9843 - precision: 0.9663 - binary_accuracy: 0.9750 - val_loss: 0.1249 - val_recall: 0.9675 - val_precision: 0.9541 - val_binary_accuracy: 0.9605
Epoch 189/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0660 - recall: 0.9857 - precision: 0.9677 - binary_accuracy: 0.9764 - val_loss: 0.1209 - val_recall: 0.9811 - val_precision: 0.9444 - val_binary_accuracy: 0.9616
Epoch 190/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0672 - recall: 0.9854 - precision: 0.9671 - binary_accuracy: 0.9760 - val_loss: 0.1242 - val_recall: 0.9596 - val_precision: 0.9575 - val_binary_accuracy: 0.9585
Epoch 191/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0667 - recall: 0.9852 - precision: 0.9677 - binary_accuracy: 0.9762 - val_loss: 0.1231 - val_recall: 0.9768 - val_precision: 0.9468 - val_binary_accuracy: 0.9610
Epoch 192/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0657 - recall: 0.9861 - precision: 0.9680 - binary_accuracy: 0.9768 - val_loss: 0.1233 - val_recall: 0.9633 - val_precision: 0.9562 - val_binary_accuracy: 0.9596
Epoch 193/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0663 - recall: 0.9854 - precision: 0.9677 - binary_accuracy: 0.9763 - val_loss: 0.1254 - val_recall: 0.9705 - val_precision: 0.9505 - val_binary_accuracy: 0.9600
Epoch 194/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0645 - recall: 0.9866 - precision: 0.9679 - binary_accuracy: 0.9770 - val_loss: 0.1277 - val_recall: 0.9553 - val_precision: 0.9567 - val_binary_accuracy: 0.9560
Epoch 195/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0674 - recall: 0.9846 - precision: 0.9670 - binary_accuracy: 0.9755 - val_loss: 0.1218 - val_recall: 0.9755 - val_precision: 0.9481 - val_binary_accuracy: 0.9611
Epoch 196/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0659 - recall: 0.9852 - precision: 0.9675 - binary_accuracy: 0.9761 - val_loss: 0.1194 - val_recall: 0.9708 - val_precision: 0.9520 - val_binary_accuracy: 0.9609
Epoch 197/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0654 - recall: 0.9860 - precision: 0.9678 - binary_accuracy: 0.9766 - val_loss: 0.1223 - val_recall: 0.9801 - val_precision: 0.9457 - val_binary_accuracy: 0.9619
Epoch 198/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0640 - recall: 0.9867 - precision: 0.9688 - binary_accuracy: 0.9775 - val_loss: 0.1244 - val_recall: 0.9690 - val_precision: 0.9512 - val_binary_accuracy: 0.9596
Epoch 199/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0659 - recall: 0.9853 - precision: 0.9681 - binary_accuracy: 0.9764 - val_loss: 0.1236 - val_recall: 0.9735 - val_precision: 0.9487 - val_binary_accuracy: 0.9604
Epoch 200/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0641 - recall: 0.9866 - precision: 0.9690 - binary_accuracy: 0.9776 - val_loss: 0.1211 - val_recall: 0.9722 - val_precision: 0.9523 - val_binary_accuracy: 0.9617
Epoch 201/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0638 - recall: 0.9867 - precision: 0.9687 - binary_accuracy: 0.9774 - val_loss: 0.1241 - val_recall: 0.9821 - val_precision: 0.9412 - val_binary_accuracy: 0.9604
Epoch 202/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0650 - recall: 0.9860 - precision: 0.9680 - binary_accuracy: 0.9767 - val_loss: 0.1233 - val_recall: 0.9680 - val_precision: 0.9537 - val_binary_accuracy: 0.9605
Epoch 203/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0648 - recall: 0.9860 - precision: 0.9687 - binary_accuracy: 0.9771 - val_loss: 0.1238 - val_recall: 0.9635 - val_precision: 0.9560 - val_binary_accuracy: 0.9596
Epoch 204/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0640 - recall: 0.9864 - precision: 0.9689 - binary_accuracy: 0.9774 - val_loss: 0.1296 - val_recall: 0.9862 - val_precision: 0.9401 - val_binary_accuracy: 0.9617
Epoch 205/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0685 - recall: 0.9836 - precision: 0.9665 - binary_accuracy: 0.9747 - val_loss: 0.1219 - val_recall: 0.9806 - val_precision: 0.9441 - val_binary_accuracy: 0.9613
Epoch 206/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0646 - recall: 0.9865 - precision: 0.9680 - binary_accuracy: 0.9770 - val_loss: 0.1201 - val_recall: 0.9694 - val_precision: 0.9545 - val_binary_accuracy: 0.9616
Epoch 207/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0639 - recall: 0.9866 - precision: 0.9694 - binary_accuracy: 0.9778 - val_loss: 0.1270 - val_recall: 0.9835 - val_precision: 0.9427 - val_binary_accuracy: 0.9619
Epoch 208/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0636 - recall: 0.9866 - precision: 0.9687 - binary_accuracy: 0.9774 - val_loss: 0.1206 - val_recall: 0.9747 - val_precision: 0.9517 - val_binary_accuracy: 0.9626
Epoch 209/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0610 - recall: 0.9880 - precision: 0.9704 - binary_accuracy: 0.9789 - val_loss: 0.1253 - val_recall: 0.9783 - val_precision: 0.9498 - val_binary_accuracy: 0.9633
Epoch 210/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0623 - recall: 0.9866 - precision: 0.9693 - binary_accuracy: 0.9777 - val_loss: 0.1255 - val_recall: 0.9810 - val_precision: 0.9473 - val_binary_accuracy: 0.9632
Epoch 211/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0623 - recall: 0.9866 - precision: 0.9699 - binary_accuracy: 0.9780 - val_loss: 0.1244 - val_recall: 0.9743 - val_precision: 0.9496 - val_binary_accuracy: 0.9613
Epoch 212/350
49/49 [==============================] - 1s 19ms/step - loss: 0.0625 - recall: 0.9866 - precision: 0.9694 - binary_accuracy: 0.9778 - val_loss: 0.1262 - val_recall: 0.9716 - val_precision: 0.9525 - val_binary_accuracy: 0.9616
Epoch 213/350
49/49 [==============================] - 1s 19ms/step - loss: 0.0629 - recall: 0.9860 - precision: 0.9693 - binary_accuracy: 0.9774 - val_loss: 0.1242 - val_recall: 0.9746 - val_precision: 0.9514 - val_binary_accuracy: 0.9624
Epoch 214/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0617 - recall: 0.9866 - precision: 0.9700 - binary_accuracy: 0.9781 - val_loss: 0.1253 - val_recall: 0.9824 - val_precision: 0.9458 - val_binary_accuracy: 0.9631
Epoch 215/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0613 - recall: 0.9874 - precision: 0.9701 - binary_accuracy: 0.9785 - val_loss: 0.1263 - val_recall: 0.9740 - val_precision: 0.9523 - val_binary_accuracy: 0.9626
Epoch 216/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0612 - recall: 0.9870 - precision: 0.9697 - binary_accuracy: 0.9781 - val_loss: 0.1227 - val_recall: 0.9819 - val_precision: 0.9464 - val_binary_accuracy: 0.9631
Epoch 217/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0608 - recall: 0.9875 - precision: 0.9701 - binary_accuracy: 0.9786 - val_loss: 0.1253 - val_recall: 0.9737 - val_precision: 0.9515 - val_binary_accuracy: 0.9621
Epoch 218/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0620 - recall: 0.9856 - precision: 0.9701 - binary_accuracy: 0.9776 - val_loss: 0.1299 - val_recall: 0.9585 - val_precision: 0.9571 - val_binary_accuracy: 0.9578
Epoch 219/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0682 - recall: 0.9846 - precision: 0.9664 - binary_accuracy: 0.9752 - val_loss: 0.1250 - val_recall: 0.9789 - val_precision: 0.9459 - val_binary_accuracy: 0.9615
Epoch 220/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0640 - recall: 0.9854 - precision: 0.9690 - binary_accuracy: 0.9770 - val_loss: 0.1280 - val_recall: 0.9826 - val_precision: 0.9424 - val_binary_accuracy: 0.9613
Epoch 221/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0606 - recall: 0.9875 - precision: 0.9705 - binary_accuracy: 0.9788 - val_loss: 0.1228 - val_recall: 0.9802 - val_precision: 0.9473 - val_binary_accuracy: 0.9629
Epoch 222/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0605 - recall: 0.9875 - precision: 0.9703 - binary_accuracy: 0.9787 - val_loss: 0.1280 - val_recall: 0.9826 - val_precision: 0.9435 - val_binary_accuracy: 0.9619
Epoch 223/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0606 - recall: 0.9876 - precision: 0.9711 - binary_accuracy: 0.9791 - val_loss: 0.1278 - val_recall: 0.9812 - val_precision: 0.9464 - val_binary_accuracy: 0.9628
Epoch 224/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0595 - recall: 0.9879 - precision: 0.9709 - binary_accuracy: 0.9791 - val_loss: 0.1298 - val_recall: 0.9578 - val_precision: 0.9593 - val_binary_accuracy: 0.9586
Epoch 225/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0601 - recall: 0.9873 - precision: 0.9704 - binary_accuracy: 0.9786 - val_loss: 0.1243 - val_recall: 0.9692 - val_precision: 0.9555 - val_binary_accuracy: 0.9621
Epoch 226/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0607 - recall: 0.9870 - precision: 0.9707 - binary_accuracy: 0.9787 - val_loss: 0.1254 - val_recall: 0.9645 - val_precision: 0.9563 - val_binary_accuracy: 0.9602
Epoch 227/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0586 - recall: 0.9878 - precision: 0.9707 - binary_accuracy: 0.9791 - val_loss: 0.1237 - val_recall: 0.9755 - val_precision: 0.9498 - val_binary_accuracy: 0.9619
Epoch 228/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0593 - recall: 0.9875 - precision: 0.9711 - binary_accuracy: 0.9791 - val_loss: 0.1280 - val_recall: 0.9772 - val_precision: 0.9468 - val_binary_accuracy: 0.9611
Epoch 229/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0627 - recall: 0.9862 - precision: 0.9695 - binary_accuracy: 0.9776 - val_loss: 0.1397 - val_recall: 0.9448 - val_precision: 0.9611 - val_binary_accuracy: 0.9533
Epoch 230/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0631 - recall: 0.9860 - precision: 0.9691 - binary_accuracy: 0.9773 - val_loss: 0.1237 - val_recall: 0.9732 - val_precision: 0.9532 - val_binary_accuracy: 0.9627
Epoch 231/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0581 - recall: 0.9878 - precision: 0.9717 - binary_accuracy: 0.9796 - val_loss: 0.1270 - val_recall: 0.9796 - val_precision: 0.9466 - val_binary_accuracy: 0.9621
Epoch 232/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0582 - recall: 0.9883 - precision: 0.9715 - binary_accuracy: 0.9796 - val_loss: 0.1260 - val_recall: 0.9777 - val_precision: 0.9499 - val_binary_accuracy: 0.9631
Epoch 233/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0586 - recall: 0.9880 - precision: 0.9717 - binary_accuracy: 0.9796 - val_loss: 0.1245 - val_recall: 0.9671 - val_precision: 0.9560 - val_binary_accuracy: 0.9613
Epoch 234/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0593 - recall: 0.9873 - precision: 0.9713 - binary_accuracy: 0.9791 - val_loss: 0.1250 - val_recall: 0.9747 - val_precision: 0.9532 - val_binary_accuracy: 0.9634
Epoch 235/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0573 - recall: 0.9888 - precision: 0.9724 - binary_accuracy: 0.9804 - val_loss: 0.1248 - val_recall: 0.9714 - val_precision: 0.9524 - val_binary_accuracy: 0.9614
Epoch 236/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0569 - recall: 0.9885 - precision: 0.9727 - binary_accuracy: 0.9804 - val_loss: 0.1288 - val_recall: 0.9827 - val_precision: 0.9444 - val_binary_accuracy: 0.9624
Epoch 237/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0584 - recall: 0.9882 - precision: 0.9710 - binary_accuracy: 0.9794 - val_loss: 0.1452 - val_recall: 0.9472 - val_precision: 0.9611 - val_binary_accuracy: 0.9544
Epoch 238/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0603 - recall: 0.9869 - precision: 0.9709 - binary_accuracy: 0.9787 - val_loss: 0.1269 - val_recall: 0.9752 - val_precision: 0.9521 - val_binary_accuracy: 0.9631
Epoch 239/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0574 - recall: 0.9880 - precision: 0.9722 - binary_accuracy: 0.9799 - val_loss: 0.1306 - val_recall: 0.9808 - val_precision: 0.9465 - val_binary_accuracy: 0.9627
Epoch 240/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0605 - recall: 0.9869 - precision: 0.9698 - binary_accuracy: 0.9781 - val_loss: 0.1346 - val_recall: 0.9555 - val_precision: 0.9603 - val_binary_accuracy: 0.9580
Epoch 241/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0588 - recall: 0.9871 - precision: 0.9722 - binary_accuracy: 0.9794 - val_loss: 0.1284 - val_recall: 0.9812 - val_precision: 0.9469 - val_binary_accuracy: 0.9631
Epoch 242/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0598 - recall: 0.9873 - precision: 0.9707 - binary_accuracy: 0.9788 - val_loss: 0.1254 - val_recall: 0.9762 - val_precision: 0.9516 - val_binary_accuracy: 0.9633
Epoch 243/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0556 - recall: 0.9891 - precision: 0.9726 - binary_accuracy: 0.9806 - val_loss: 0.1249 - val_recall: 0.9720 - val_precision: 0.9558 - val_binary_accuracy: 0.9635
Epoch 244/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0558 - recall: 0.9881 - precision: 0.9730 - binary_accuracy: 0.9804 - val_loss: 0.1260 - val_recall: 0.9809 - val_precision: 0.9478 - val_binary_accuracy: 0.9634
Epoch 245/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0555 - recall: 0.9887 - precision: 0.9730 - binary_accuracy: 0.9807 - val_loss: 0.1311 - val_recall: 0.9678 - val_precision: 0.9513 - val_binary_accuracy: 0.9591
Epoch 246/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0562 - recall: 0.9884 - precision: 0.9730 - binary_accuracy: 0.9805 - val_loss: 0.1375 - val_recall: 0.9878 - val_precision: 0.9374 - val_binary_accuracy: 0.9609
Epoch 247/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0559 - recall: 0.9883 - precision: 0.9726 - binary_accuracy: 0.9803 - val_loss: 0.1280 - val_recall: 0.9748 - val_precision: 0.9504 - val_binary_accuracy: 0.9620
Epoch 248/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0553 - recall: 0.9890 - precision: 0.9734 - binary_accuracy: 0.9810 - val_loss: 0.1304 - val_recall: 0.9794 - val_precision: 0.9494 - val_binary_accuracy: 0.9636
Epoch 249/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0555 - recall: 0.9882 - precision: 0.9731 - binary_accuracy: 0.9805 - val_loss: 0.1306 - val_recall: 0.9675 - val_precision: 0.9539 - val_binary_accuracy: 0.9604
Epoch 250/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0562 - recall: 0.9883 - precision: 0.9724 - binary_accuracy: 0.9801 - val_loss: 0.1360 - val_recall: 0.9620 - val_precision: 0.9567 - val_binary_accuracy: 0.9592
Epoch 251/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0586 - recall: 0.9867 - precision: 0.9716 - binary_accuracy: 0.9789 - val_loss: 0.1317 - val_recall: 0.9705 - val_precision: 0.9547 - val_binary_accuracy: 0.9622
Epoch 252/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0556 - recall: 0.9890 - precision: 0.9734 - binary_accuracy: 0.9810 - val_loss: 0.1353 - val_recall: 0.9773 - val_precision: 0.9454 - val_binary_accuracy: 0.9604
Epoch 253/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0548 - recall: 0.9889 - precision: 0.9735 - binary_accuracy: 0.9810 - val_loss: 0.1317 - val_recall: 0.9768 - val_precision: 0.9510 - val_binary_accuracy: 0.9632
Epoch 254/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0559 - recall: 0.9881 - precision: 0.9730 - binary_accuracy: 0.9804 - val_loss: 0.1316 - val_recall: 0.9812 - val_precision: 0.9468 - val_binary_accuracy: 0.9631
Epoch 255/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0599 - recall: 0.9863 - precision: 0.9705 - binary_accuracy: 0.9782 - val_loss: 0.1298 - val_recall: 0.9734 - val_precision: 0.9525 - val_binary_accuracy: 0.9624
Epoch 256/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0558 - recall: 0.9886 - precision: 0.9727 - binary_accuracy: 0.9804 - val_loss: 0.1309 - val_recall: 0.9733 - val_precision: 0.9539 - val_binary_accuracy: 0.9631
Epoch 257/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0542 - recall: 0.9891 - precision: 0.9737 - binary_accuracy: 0.9812 - val_loss: 0.1281 - val_recall: 0.9811 - val_precision: 0.9470 - val_binary_accuracy: 0.9631
Epoch 258/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0553 - recall: 0.9884 - precision: 0.9727 - binary_accuracy: 0.9803 - val_loss: 0.1309 - val_recall: 0.9755 - val_precision: 0.9523 - val_binary_accuracy: 0.9633
Epoch 259/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0561 - recall: 0.9883 - precision: 0.9724 - binary_accuracy: 0.9802 - val_loss: 0.1306 - val_recall: 0.9687 - val_precision: 0.9548 - val_binary_accuracy: 0.9614
Epoch 260/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0539 - recall: 0.9889 - precision: 0.9737 - binary_accuracy: 0.9811 - val_loss: 0.1386 - val_recall: 0.9542 - val_precision: 0.9587 - val_binary_accuracy: 0.9565
Epoch 261/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0552 - recall: 0.9883 - precision: 0.9732 - binary_accuracy: 0.9806 - val_loss: 0.1324 - val_recall: 0.9792 - val_precision: 0.9475 - val_binary_accuracy: 0.9624
Epoch 262/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0556 - recall: 0.9886 - precision: 0.9730 - binary_accuracy: 0.9806 - val_loss: 0.1403 - val_recall: 0.9839 - val_precision: 0.9415 - val_binary_accuracy: 0.9614
Epoch 263/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0551 - recall: 0.9887 - precision: 0.9734 - binary_accuracy: 0.9808 - val_loss: 0.1291 - val_recall: 0.9714 - val_precision: 0.9532 - val_binary_accuracy: 0.9618
Epoch 264/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0546 - recall: 0.9883 - precision: 0.9735 - binary_accuracy: 0.9807 - val_loss: 0.1323 - val_recall: 0.9789 - val_precision: 0.9486 - val_binary_accuracy: 0.9629
Epoch 265/350
49/49 [==============================] - 1s 18ms/step - loss: 0.0517 - recall: 0.9900 - precision: 0.9750 - binary_accuracy: 0.9823 - val_loss: 0.1340 - val_recall: 0.9815 - val_precision: 0.9463 - val_binary_accuracy: 0.9629
Epoch 266/350
49/49 [==============================] - 1s 18ms/step - loss: 0.0536 - recall: 0.9886 - precision: 0.9740 - binary_accuracy: 0.9811 - val_loss: 0.1299 - val_recall: 0.9704 - val_precision: 0.9546 - val_binary_accuracy: 0.9621
Epoch 267/350
49/49 [==============================] - 1s 24ms/step - loss: 0.0519 - recall: 0.9895 - precision: 0.9745 - binary_accuracy: 0.9819 - val_loss: 0.1340 - val_recall: 0.9779 - val_precision: 0.9501 - val_binary_accuracy: 0.9632
Epoch 268/350
49/49 [==============================] - 1s 20ms/step - loss: 0.0539 - recall: 0.9886 - precision: 0.9739 - binary_accuracy: 0.9811 - val_loss: 0.1338 - val_recall: 0.9762 - val_precision: 0.9487 - val_binary_accuracy: 0.9617
Epoch 269/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0527 - recall: 0.9898 - precision: 0.9748 - binary_accuracy: 0.9821 - val_loss: 0.1376 - val_recall: 0.9603 - val_precision: 0.9587 - val_binary_accuracy: 0.9595
Epoch 270/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0525 - recall: 0.9890 - precision: 0.9745 - binary_accuracy: 0.9816 - val_loss: 0.1291 - val_recall: 0.9745 - val_precision: 0.9530 - val_binary_accuracy: 0.9632
Epoch 271/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0532 - recall: 0.9886 - precision: 0.9741 - binary_accuracy: 0.9812 - val_loss: 0.1382 - val_recall: 0.9834 - val_precision: 0.9459 - val_binary_accuracy: 0.9636
Epoch 272/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0534 - recall: 0.9890 - precision: 0.9739 - binary_accuracy: 0.9813 - val_loss: 0.1313 - val_recall: 0.9677 - val_precision: 0.9582 - val_binary_accuracy: 0.9627
Epoch 273/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0539 - recall: 0.9880 - precision: 0.9742 - binary_accuracy: 0.9809 - val_loss: 0.1412 - val_recall: 0.9777 - val_precision: 0.9476 - val_binary_accuracy: 0.9618
Epoch 274/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0532 - recall: 0.9887 - precision: 0.9741 - binary_accuracy: 0.9812 - val_loss: 0.1371 - val_recall: 0.9787 - val_precision: 0.9463 - val_binary_accuracy: 0.9616
Epoch 275/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0526 - recall: 0.9888 - precision: 0.9743 - binary_accuracy: 0.9814 - val_loss: 0.1428 - val_recall: 0.9869 - val_precision: 0.9385 - val_binary_accuracy: 0.9611
Epoch 276/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0523 - recall: 0.9894 - precision: 0.9744 - binary_accuracy: 0.9817 - val_loss: 0.1374 - val_recall: 0.9559 - val_precision: 0.9611 - val_binary_accuracy: 0.9586
Epoch 277/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0548 - recall: 0.9882 - precision: 0.9737 - binary_accuracy: 0.9808 - val_loss: 0.1317 - val_recall: 0.9800 - val_precision: 0.9497 - val_binary_accuracy: 0.9640
Epoch 278/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0553 - recall: 0.9877 - precision: 0.9730 - binary_accuracy: 0.9801 - val_loss: 0.1433 - val_recall: 0.9879 - val_precision: 0.9384 - val_binary_accuracy: 0.9615
Epoch 279/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0503 - recall: 0.9905 - precision: 0.9754 - binary_accuracy: 0.9827 - val_loss: 0.1321 - val_recall: 0.9720 - val_precision: 0.9531 - val_binary_accuracy: 0.9621
Epoch 280/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0515 - recall: 0.9894 - precision: 0.9752 - binary_accuracy: 0.9821 - val_loss: 0.1359 - val_recall: 0.9791 - val_precision: 0.9476 - val_binary_accuracy: 0.9625
Epoch 281/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0507 - recall: 0.9900 - precision: 0.9758 - binary_accuracy: 0.9827 - val_loss: 0.1326 - val_recall: 0.9642 - val_precision: 0.9568 - val_binary_accuracy: 0.9604
Epoch 282/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0516 - recall: 0.9893 - precision: 0.9754 - binary_accuracy: 0.9822 - val_loss: 0.1352 - val_recall: 0.9693 - val_precision: 0.9550 - val_binary_accuracy: 0.9618
Epoch 283/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0517 - recall: 0.9890 - precision: 0.9752 - binary_accuracy: 0.9819 - val_loss: 0.1388 - val_recall: 0.9742 - val_precision: 0.9479 - val_binary_accuracy: 0.9603
Epoch 284/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0500 - recall: 0.9903 - precision: 0.9755 - binary_accuracy: 0.9827 - val_loss: 0.1439 - val_recall: 0.9624 - val_precision: 0.9534 - val_binary_accuracy: 0.9577
Epoch 285/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0490 - recall: 0.9904 - precision: 0.9762 - binary_accuracy: 0.9831 - val_loss: 0.1358 - val_recall: 0.9653 - val_precision: 0.9577 - val_binary_accuracy: 0.9613
Epoch 286/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0490 - recall: 0.9910 - precision: 0.9760 - binary_accuracy: 0.9833 - val_loss: 0.1390 - val_recall: 0.9727 - val_precision: 0.9534 - val_binary_accuracy: 0.9626
Epoch 287/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0539 - recall: 0.9880 - precision: 0.9748 - binary_accuracy: 0.9813 - val_loss: 0.1466 - val_recall: 0.9800 - val_precision: 0.9427 - val_binary_accuracy: 0.9602
Epoch 288/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0513 - recall: 0.9897 - precision: 0.9751 - binary_accuracy: 0.9822 - val_loss: 0.1386 - val_recall: 0.9593 - val_precision: 0.9591 - val_binary_accuracy: 0.9592
Epoch 289/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0494 - recall: 0.9894 - precision: 0.9764 - binary_accuracy: 0.9828 - val_loss: 0.1413 - val_recall: 0.9842 - val_precision: 0.9427 - val_binary_accuracy: 0.9622
Epoch 290/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0512 - recall: 0.9894 - precision: 0.9754 - binary_accuracy: 0.9822 - val_loss: 0.1377 - val_recall: 0.9753 - val_precision: 0.9521 - val_binary_accuracy: 0.9631
Epoch 291/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0507 - recall: 0.9899 - precision: 0.9759 - binary_accuracy: 0.9827 - val_loss: 0.1342 - val_recall: 0.9726 - val_precision: 0.9528 - val_binary_accuracy: 0.9622
Epoch 292/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0510 - recall: 0.9894 - precision: 0.9749 - binary_accuracy: 0.9820 - val_loss: 0.1428 - val_recall: 0.9548 - val_precision: 0.9610 - val_binary_accuracy: 0.9580
Epoch 293/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0516 - recall: 0.9888 - precision: 0.9750 - binary_accuracy: 0.9817 - val_loss: 0.1333 - val_recall: 0.9729 - val_precision: 0.9538 - val_binary_accuracy: 0.9629
Epoch 294/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0494 - recall: 0.9899 - precision: 0.9760 - binary_accuracy: 0.9828 - val_loss: 0.1422 - val_recall: 0.9625 - val_precision: 0.9563 - val_binary_accuracy: 0.9592
Epoch 295/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0519 - recall: 0.9885 - precision: 0.9752 - binary_accuracy: 0.9817 - val_loss: 0.1415 - val_recall: 0.9820 - val_precision: 0.9463 - val_binary_accuracy: 0.9631
Epoch 296/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0503 - recall: 0.9897 - precision: 0.9761 - binary_accuracy: 0.9827 - val_loss: 0.1421 - val_recall: 0.9839 - val_precision: 0.9427 - val_binary_accuracy: 0.9620
Epoch 297/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0475 - recall: 0.9905 - precision: 0.9771 - binary_accuracy: 0.9837 - val_loss: 0.1450 - val_recall: 0.9859 - val_precision: 0.9422 - val_binary_accuracy: 0.9627
Epoch 298/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0492 - recall: 0.9900 - precision: 0.9760 - binary_accuracy: 0.9828 - val_loss: 0.1381 - val_recall: 0.9678 - val_precision: 0.9544 - val_binary_accuracy: 0.9608
Epoch 299/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0494 - recall: 0.9892 - precision: 0.9769 - binary_accuracy: 0.9829 - val_loss: 0.1426 - val_recall: 0.9823 - val_precision: 0.9467 - val_binary_accuracy: 0.9635
Epoch 300/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0491 - recall: 0.9897 - precision: 0.9760 - binary_accuracy: 0.9827 - val_loss: 0.1392 - val_recall: 0.9783 - val_precision: 0.9498 - val_binary_accuracy: 0.9633
Epoch 301/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0517 - recall: 0.9890 - precision: 0.9746 - binary_accuracy: 0.9816 - val_loss: 0.1397 - val_recall: 0.9817 - val_precision: 0.9454 - val_binary_accuracy: 0.9625
Epoch 302/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0471 - recall: 0.9913 - precision: 0.9768 - binary_accuracy: 0.9839 - val_loss: 0.1372 - val_recall: 0.9682 - val_precision: 0.9546 - val_binary_accuracy: 0.9611
Epoch 303/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0487 - recall: 0.9893 - precision: 0.9767 - binary_accuracy: 0.9829 - val_loss: 0.1366 - val_recall: 0.9723 - val_precision: 0.9522 - val_binary_accuracy: 0.9617
Epoch 304/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0483 - recall: 0.9899 - precision: 0.9770 - binary_accuracy: 0.9833 - val_loss: 0.1427 - val_recall: 0.9808 - val_precision: 0.9471 - val_binary_accuracy: 0.9630
Epoch 305/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0492 - recall: 0.9899 - precision: 0.9764 - binary_accuracy: 0.9830 - val_loss: 0.1347 - val_recall: 0.9738 - val_precision: 0.9512 - val_binary_accuracy: 0.9619
Epoch 306/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0525 - recall: 0.9882 - precision: 0.9745 - binary_accuracy: 0.9812 - val_loss: 0.1379 - val_recall: 0.9727 - val_precision: 0.9483 - val_binary_accuracy: 0.9598
Epoch 307/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0463 - recall: 0.9911 - precision: 0.9779 - binary_accuracy: 0.9844 - val_loss: 0.1381 - val_recall: 0.9818 - val_precision: 0.9469 - val_binary_accuracy: 0.9634
Epoch 308/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0475 - recall: 0.9906 - precision: 0.9772 - binary_accuracy: 0.9837 - val_loss: 0.1406 - val_recall: 0.9812 - val_precision: 0.9479 - val_binary_accuracy: 0.9636
Epoch 309/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0484 - recall: 0.9897 - precision: 0.9764 - binary_accuracy: 0.9829 - val_loss: 0.1408 - val_recall: 0.9690 - val_precision: 0.9521 - val_binary_accuracy: 0.9601
Epoch 310/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0470 - recall: 0.9905 - precision: 0.9771 - binary_accuracy: 0.9836 - val_loss: 0.1398 - val_recall: 0.9778 - val_precision: 0.9503 - val_binary_accuracy: 0.9634
Epoch 311/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0452 - recall: 0.9916 - precision: 0.9786 - binary_accuracy: 0.9850 - val_loss: 0.1442 - val_recall: 0.9592 - val_precision: 0.9599 - val_binary_accuracy: 0.9595
Epoch 312/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0496 - recall: 0.9891 - precision: 0.9768 - binary_accuracy: 0.9828 - val_loss: 0.1525 - val_recall: 0.9865 - val_precision: 0.9397 - val_binary_accuracy: 0.9616
Epoch 313/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0493 - recall: 0.9898 - precision: 0.9762 - binary_accuracy: 0.9829 - val_loss: 0.1396 - val_recall: 0.9786 - val_precision: 0.9490 - val_binary_accuracy: 0.9630
Epoch 314/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0478 - recall: 0.9897 - precision: 0.9767 - binary_accuracy: 0.9830 - val_loss: 0.1393 - val_recall: 0.9794 - val_precision: 0.9494 - val_binary_accuracy: 0.9636
Epoch 315/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0504 - recall: 0.9880 - precision: 0.9756 - binary_accuracy: 0.9817 - val_loss: 0.1428 - val_recall: 0.9822 - val_precision: 0.9473 - val_binary_accuracy: 0.9638
Epoch 316/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0456 - recall: 0.9908 - precision: 0.9785 - binary_accuracy: 0.9845 - val_loss: 0.1477 - val_recall: 0.9850 - val_precision: 0.9397 - val_binary_accuracy: 0.9609
Epoch 317/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0485 - recall: 0.9902 - precision: 0.9766 - binary_accuracy: 0.9833 - val_loss: 0.1441 - val_recall: 0.9625 - val_precision: 0.9580 - val_binary_accuracy: 0.9601
Epoch 318/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0457 - recall: 0.9913 - precision: 0.9784 - binary_accuracy: 0.9847 - val_loss: 0.1408 - val_recall: 0.9699 - val_precision: 0.9560 - val_binary_accuracy: 0.9626
Epoch 319/350
49/49 [==============================] - 1s 18ms/step - loss: 0.0439 - recall: 0.9919 - precision: 0.9790 - binary_accuracy: 0.9854 - val_loss: 0.1411 - val_recall: 0.9817 - val_precision: 0.9467 - val_binary_accuracy: 0.9632
Epoch 320/350
49/49 [==============================] - 1s 20ms/step - loss: 0.0456 - recall: 0.9907 - precision: 0.9778 - binary_accuracy: 0.9841 - val_loss: 0.1514 - val_recall: 0.9508 - val_precision: 0.9601 - val_binary_accuracy: 0.9556
Epoch 321/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0469 - recall: 0.9902 - precision: 0.9775 - binary_accuracy: 0.9837 - val_loss: 0.1393 - val_recall: 0.9764 - val_precision: 0.9534 - val_binary_accuracy: 0.9643
Epoch 322/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0472 - recall: 0.9897 - precision: 0.9774 - binary_accuracy: 0.9834 - val_loss: 0.1419 - val_recall: 0.9769 - val_precision: 0.9485 - val_binary_accuracy: 0.9619
Epoch 323/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0461 - recall: 0.9906 - precision: 0.9777 - binary_accuracy: 0.9840 - val_loss: 0.1418 - val_recall: 0.9667 - val_precision: 0.9572 - val_binary_accuracy: 0.9617
Epoch 324/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0454 - recall: 0.9907 - precision: 0.9783 - binary_accuracy: 0.9844 - val_loss: 0.1417 - val_recall: 0.9785 - val_precision: 0.9497 - val_binary_accuracy: 0.9633
Epoch 325/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0454 - recall: 0.9907 - precision: 0.9779 - binary_accuracy: 0.9841 - val_loss: 0.1589 - val_recall: 0.9877 - val_precision: 0.9367 - val_binary_accuracy: 0.9604
Epoch 326/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0502 - recall: 0.9887 - precision: 0.9758 - binary_accuracy: 0.9821 - val_loss: 0.1490 - val_recall: 0.9834 - val_precision: 0.9438 - val_binary_accuracy: 0.9625
Epoch 327/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0469 - recall: 0.9905 - precision: 0.9769 - binary_accuracy: 0.9835 - val_loss: 0.1417 - val_recall: 0.9794 - val_precision: 0.9490 - val_binary_accuracy: 0.9634
Epoch 328/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0477 - recall: 0.9895 - precision: 0.9772 - binary_accuracy: 0.9832 - val_loss: 0.1455 - val_recall: 0.9834 - val_precision: 0.9438 - val_binary_accuracy: 0.9624
Epoch 329/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0483 - recall: 0.9899 - precision: 0.9763 - binary_accuracy: 0.9829 - val_loss: 0.1483 - val_recall: 0.9836 - val_precision: 0.9459 - val_binary_accuracy: 0.9636
Epoch 330/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0450 - recall: 0.9911 - precision: 0.9783 - binary_accuracy: 0.9845 - val_loss: 0.1438 - val_recall: 0.9716 - val_precision: 0.9524 - val_binary_accuracy: 0.9615
Epoch 331/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0439 - recall: 0.9917 - precision: 0.9791 - binary_accuracy: 0.9853 - val_loss: 0.1415 - val_recall: 0.9725 - val_precision: 0.9525 - val_binary_accuracy: 0.9620
Epoch 332/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0445 - recall: 0.9911 - precision: 0.9792 - binary_accuracy: 0.9850 - val_loss: 0.1420 - val_recall: 0.9787 - val_precision: 0.9507 - val_binary_accuracy: 0.9640
Epoch 333/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0432 - recall: 0.9918 - precision: 0.9792 - binary_accuracy: 0.9854 - val_loss: 0.1473 - val_recall: 0.9801 - val_precision: 0.9472 - val_binary_accuracy: 0.9627
Epoch 334/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0435 - recall: 0.9915 - precision: 0.9788 - binary_accuracy: 0.9851 - val_loss: 0.1411 - val_recall: 0.9677 - val_precision: 0.9570 - val_binary_accuracy: 0.9621
Epoch 335/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0451 - recall: 0.9907 - precision: 0.9783 - binary_accuracy: 0.9844 - val_loss: 0.1527 - val_recall: 0.9785 - val_precision: 0.9449 - val_binary_accuracy: 0.9607
Epoch 336/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0443 - recall: 0.9913 - precision: 0.9791 - binary_accuracy: 0.9851 - val_loss: 0.1482 - val_recall: 0.9817 - val_precision: 0.9471 - val_binary_accuracy: 0.9634
Epoch 337/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0459 - recall: 0.9902 - precision: 0.9777 - binary_accuracy: 0.9838 - val_loss: 0.1462 - val_recall: 0.9834 - val_precision: 0.9452 - val_binary_accuracy: 0.9632
Epoch 338/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0452 - recall: 0.9910 - precision: 0.9779 - binary_accuracy: 0.9843 - val_loss: 0.1429 - val_recall: 0.9699 - val_precision: 0.9554 - val_binary_accuracy: 0.9623
Epoch 339/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0434 - recall: 0.9914 - precision: 0.9794 - binary_accuracy: 0.9853 - val_loss: 0.1491 - val_recall: 0.9827 - val_precision: 0.9474 - val_binary_accuracy: 0.9640
Epoch 340/350
49/49 [==============================] - 1s 13ms/step - loss: 0.0439 - recall: 0.9911 - precision: 0.9788 - binary_accuracy: 0.9848 - val_loss: 0.1478 - val_recall: 0.9797 - val_precision: 0.9472 - val_binary_accuracy: 0.9625
Epoch 341/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0440 - recall: 0.9906 - precision: 0.9790 - binary_accuracy: 0.9847 - val_loss: 0.1424 - val_recall: 0.9734 - val_precision: 0.9519 - val_binary_accuracy: 0.9621
Epoch 342/350
49/49 [==============================] - 1s 17ms/step - loss: 0.0429 - recall: 0.9918 - precision: 0.9791 - binary_accuracy: 0.9853 - val_loss: 0.1439 - val_recall: 0.9772 - val_precision: 0.9524 - val_binary_accuracy: 0.9642
Epoch 343/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0406 - recall: 0.9926 - precision: 0.9804 - binary_accuracy: 0.9864 - val_loss: 0.1415 - val_recall: 0.9742 - val_precision: 0.9526 - val_binary_accuracy: 0.9629
Epoch 344/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0410 - recall: 0.9927 - precision: 0.9804 - binary_accuracy: 0.9865 - val_loss: 0.1483 - val_recall: 0.9756 - val_precision: 0.9529 - val_binary_accuracy: 0.9637
Epoch 345/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0425 - recall: 0.9920 - precision: 0.9794 - binary_accuracy: 0.9856 - val_loss: 0.1480 - val_recall: 0.9776 - val_precision: 0.9474 - val_binary_accuracy: 0.9617
Epoch 346/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0404 - recall: 0.9927 - precision: 0.9805 - binary_accuracy: 0.9865 - val_loss: 0.1442 - val_recall: 0.9784 - val_precision: 0.9516 - val_binary_accuracy: 0.9643
Epoch 347/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0430 - recall: 0.9907 - precision: 0.9792 - binary_accuracy: 0.9849 - val_loss: 0.1506 - val_recall: 0.9795 - val_precision: 0.9484 - val_binary_accuracy: 0.9631
Epoch 348/350
49/49 [==============================] - 1s 15ms/step - loss: 0.0430 - recall: 0.9916 - precision: 0.9796 - binary_accuracy: 0.9855 - val_loss: 0.1552 - val_recall: 0.9689 - val_precision: 0.9500 - val_binary_accuracy: 0.9590
Epoch 349/350
49/49 [==============================] - 1s 16ms/step - loss: 0.0457 - recall: 0.9899 - precision: 0.9783 - binary_accuracy: 0.9840 - val_loss: 0.1509 - val_recall: 0.9754 - val_precision: 0.9502 - val_binary_accuracy: 0.9621
Epoch 350/350
49/49 [==============================] - 1s 14ms/step - loss: 0.0422 - recall: 0.9919 - precision: 0.9793 - binary_accuracy: 0.9855 - val_loss: 0.1422 - val_recall: 0.9737 - val_precision: 0.9547 - val_binary_accuracy: 0.9637
443/443 [==============================] - 1s 3ms/step - loss: 0.1476 - recall: 0.9739 - precision: 0.9519 - binary_accuracy: 0.9621
Test recall:  0.9739057421684265
443/443 [==============================] - 1s 2ms/step


# Print confusion matrix of ann
confusion_matrix = metrics.confusion_matrix(y_test_rete,y_pred)
cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.show()

# Print classification report and other scores
print(classification_report(y_test_rete, y_pred))
print("Recall score:", recall_score(y_test_rete, y_pred, average="macro"))
print("Precision score:", precision_score(y_test_rete, y_pred))
print("f1_score score:", f1_score(y_test_rete, y_pred))
print("Accuracy:", accuracy_score(y_test_rete, y_pred))

              precision    recall  f1-score   support

           0       0.97      0.95      0.96      7025
           1       0.95      0.97      0.96      7128

    accuracy                           0.96     14153
   macro avg       0.96      0.96      0.96     14153
weighted avg       0.96      0.96      0.96     14153

Recall score: 0.9619706555471681
Precision score: 0.9518716577540107
f1_score score: 0.9627626378198462
Accuracy: 0.9620575143079206


set_scores(results_test_neural,"ANN",y_test_rete,y_pred)


X_train_mlp, X_test_mlp, y_train_mlp, y_test_mlp = train_test_split(df_neural_X, df_neural_Y, test_size=0.33, random_state=42)


MLP = MLPClassifier(max_iter=5000,random_state=42)
MLP.fit(X_train_mlp, y_train_mlp)

MLPClassifier(max_iter=5000, random_state=42)

MLPClassifier(max_iter=5000, random_state=42)


y_train_MLP_predicted = MLP.predict(X_train_mlp)


confusion_matrix = metrics.confusion_matrix(y_train_mlp,y_train_MLP_predicted)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.grid(False)
plt.show()

print(classification_report(y_train_mlp, y_train_MLP_predicted))

              precision    recall  f1-score   support

           0       0.81      0.92      0.86     47408
           1       0.90      0.78      0.84     47413

    accuracy                           0.85     94821
   macro avg       0.86      0.85      0.85     94821
weighted avg       0.86      0.85      0.85     94821


y_test_MLP_predicted = MLP.predict(X_test_mlp)


confusion_matrix = metrics.confusion_matrix(y_test_mlp,y_test_MLP_predicted)

cm_display = metrics.ConfusionMatrixDisplay(confusion_matrix = confusion_matrix, display_labels = [0, 1])
fig, ax = plt.subplots(figsize=(3, 3))
cm_display.plot(ax=ax, values_format='d')
plt.grid(False)
plt.show()

print(classification_report(y_test_mlp, y_test_MLP_predicted))

              precision    recall  f1-score   support

           0       0.81      0.92      0.86     23354
           1       0.90      0.78      0.84     23349

    accuracy                           0.85     46703
   macro avg       0.86      0.85      0.85     46703
weighted avg       0.86      0.85      0.85     46703


set_scores(results_test_neural,"MLP",y_test_mlp,y_test_MLP_predicted)


results_test_neural


data_frame = results_test_neural.sort_values('accuracy', ascending=False)

plt.figure(figsize=(6,5))
plt.bar(data_frame.index, data_frame['accuracy'])
fig.show()
plt.ylabel('Accuracy',  fontsize=20)
plt.xlabel('Reti neurali',  fontsize=20)
ax = plt.title('Accuracy delle reti neurali',  fontsize=19)


data_frame = results_test_neural.sort_values('f1', ascending=False)

plt.figure(figsize=(6,5))
plt.bar(data_frame.index, data_frame['f1'])
fig.show()
plt.ylabel('F1 score',  fontsize=20)
plt.xlabel('Reti neurali',  fontsize=20)
ax = plt.title('F1 score delle reti neurali',  fontsize=19)


data_frame = results_test_neural.sort_values('precision', ascending=False)

plt.figure(figsize=(6,5))
plt.bar(data_frame.index, data_frame['precision'])
fig.show()
plt.ylabel('Precision',  fontsize=20)
plt.xlabel('Reti neurali',  fontsize=20)
ax = plt.title('Precision delle reti neurali',  fontsize=19)


data_frame = results_test_neural.sort_values('recall', ascending=False)

plt.figure(figsize=(6,5))
plt.bar(data_frame.index, data_frame['recall'])
fig.show()
plt.ylabel('Recall',  fontsize=20)
plt.xlabel('Reti neurali',  fontsize=20)
ax = plt.title('Recall delle reti neurali',  fontsize=19)

	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustSpeed	WindSpeed9am	WindSpeed3pm	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
count	143975.000000	144199.000000	142199.000000	82670.000000	75625.000000	135197.000000	143693.000000	142398.000000	142806.000000	140953.000000	130395.00000	130432.000000	89572.000000	86102.000000	143693.000000	141851.00000
mean	12.194034	23.221348	2.360918	5.468232	7.611178	40.035230	14.043426	18.662657	68.880831	51.539116	1017.64994	1015.255889	4.447461	4.509930	16.990631	21.68339
std	6.398495	7.119049	8.478060	4.193704	3.785483	13.607062	8.915375	8.809800	19.029164	20.795902	7.10653	7.037414	2.887159	2.720357	6.488753	6.93665
min	-8.500000	-4.800000	0.000000	0.000000	0.000000	6.000000	0.000000	0.000000	0.000000	0.000000	980.50000	977.100000	0.000000	0.000000	-7.200000	-5.40000
25%	7.600000	17.900000	0.000000	2.600000	4.800000	31.000000	7.000000	13.000000	57.000000	37.000000	1012.90000	1010.400000	1.000000	2.000000	12.300000	16.60000
50%	12.000000	22.600000	0.000000	4.800000	8.400000	39.000000	13.000000	19.000000	70.000000	52.000000	1017.60000	1015.200000	5.000000	5.000000	16.700000	21.10000
75%	16.900000	28.200000	0.800000	7.400000	10.600000	48.000000	19.000000	24.000000	83.000000	66.000000	1022.40000	1020.000000	7.000000	7.000000	21.600000	26.40000
max	33.900000	48.100000	371.000000	145.000000	14.500000	135.000000	130.000000	87.000000	100.000000	100.000000	1041.00000	1039.600000	9.000000	9.000000	40.200000	46.70000

	Date	Location	MinTemp	MaxTemp	Rainfall	Evaporation	Sunshine	WindGustDir	WindGustSpeed	WindDir9am	...	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm	RainToday	RainTomorrow
83256	2015-06-06	Dartmoor	10.9	17.2	0.0	0.2	5.6	N	37.0	NNW	...	NaN	NaN	1028.0	1025.0	NaN	NaN	12.0	16.9	No	No
20219	2015-01-08	NorahHead	21.4	29.6	0.0	NaN	NaN	NE	61.0	NNE	...	72.0	74.0	1016.1	1011.8	NaN	NaN	24.2	25.2	No	No
44673	2014-12-25	Wollongong	18.8	25.4	0.0	NaN	NaN	NNE	31.0	NE	...	88.0	87.0	1011.3	1007.3	8.0	8.0	20.5	21.6	No	Yes
115998	2012-11-09	PearceRAAF	11.4	33.5	0.0	NaN	13.0	WSW	43.0	NNE	...	19.0	16.0	1016.9	1013.6	0.0	3.0	27.6	30.9	No	No
5715	2016-07-27	BadgerysCreek	6.5	18.1	0.0	NaN	NaN	WNW	50.0	N	...	56.0	43.0	1012.3	1013.9	NaN	NaN	15.1	17.1	No	No
7981	2014-07-15	Cobar	6.8	17.7	0.0	2.4	NaN	N	35.0	ENE	...	54.0	39.0	1020.2	1016.2	8.0	8.0	11.9	17.2	No	No
62057	2011-06-25	Sale	3.8	18.5	0.0	1.0	6.8	NNE	19.0	WNW	...	86.0	54.0	1028.4	1025.4	2.0	2.0	8.4	17.4	No	No
6396	2009-12-14	Cobar	18.9	35.9	0.0	12.8	12.4	WSW	39.0	ESE	...	23.0	11.0	1016.5	1014.0	1.0	1.0	27.1	34.5	No	No
81073	2009-03-17	Dartmoor	11.1	15.9	0.2	3.0	0.0	SSW	31.0	SSW	...	75.0	74.0	1019.9	1019.7	NaN	NaN	13.5	15.2	No	No
48448	2015-11-29	Canberra	15.9	27.4	0.0	NaN	NaN	WSW	41.0	NW	...	64.0	25.0	1013.0	1009.7	8.0	NaN	19.4	25.5	No	No
115504	2011-07-04	PearceRAAF	0.7	15.0	0.0	NaN	7.6	ESE	28.0	SW	...	93.0	46.0	1028.6	1027.2	1.0	3.0	5.8	14.6	No	No
128266	2013-03-07	Walpole	16.4	23.4	1.0	NaN	NaN	SE	39.0	SE	...	61.0	57.0	1021.3	1018.7	NaN	NaN	19.4	21.4	No	No
91560	2012-08-12	GoldCoast	10.7	21.3	0.0	NaN	NaN	S	59.0	SSW	...	53.0	49.0	1020.2	1018.0	NaN	NaN	17.2	19.6	No	No
56309	2012-04-21	Ballarat	7.4	23.2	0.0	NaN	NaN	N	37.0	NNE	...	84.0	49.0	1016.0	1012.4	0.0	NaN	17.4	22.2	No	Yes
51043	2014-09-11	Tuggeranong	1.7	16.9	0.0	NaN	NaN	W	44.0	W	...	52.0	44.0	1016.8	1015.5	NaN	NaN	14.1	16.0	No	No
36899	2010-01-06	WaggaWagga	18.6	34.5	6.0	12.2	13.7	W	54.0	NNE	...	59.0	11.0	1014.2	1011.6	0.0	2.0	24.9	33.6	Yes	No
24788	2010-09-23	Penrith	14.2	20.4	NaN	NaN	NaN	SE	24.0	SSW	...	80.0	65.0	NaN	NaN	NaN	NaN	15.9	18.2	NaN	No
18573	2010-04-04	NorahHead	15.9	21.7	13.4	NaN	NaN	S	46.0	S	...	69.0	73.0	1022.1	1019.6	NaN	NaN	20.3	19.8	Yes	No
23087	2014-08-20	NorfolkIsland	16.1	19.8	0.6	4.2	9.9	W	59.0	WNW	...	82.0	70.0	1010.8	1009.9	3.0	1.0	18.0	19.1	No	No
108474	2017-03-21	Woomera	17.7	30.7	0.0	12.2	0.0	SW	43.0	SW	...	68.0	30.0	1011.9	1010.6	1.0	NaN	19.5	28.7	No	No
86050	2014-05-03	Brisbane	15.4	21.1	13.8	6.0	9.0	WNW	44.0	W	...	52.0	33.0	1005.8	1004.3	5.0	6.0	16.9	19.2	Yes	No
125817	2014-09-15	SalmonGums	0.3	21.9	0.0	NaN	NaN	SSW	33.0	ESE	...	45.0	37.0	NaN	NaN	NaN	NaN	16.5	21.0	No	No
729	2010-11-30	Albury	14.4	23.3	1.6	NaN	NaN	SE	35.0	SE	...	69.0	81.0	1015.0	1014.3	NaN	NaN	17.4	19.5	Yes	Yes
29397	2015-05-09	Richmond	4.0	21.2	0.0	NaN	NaN	W	35.0	NE	...	74.0	40.0	1017.9	1013.9	NaN	1.0	11.4	20.8	No	No
41093	2013-07-03	Williamtown	7.0	18.1	0.2	2.6	8.7	NW	24.0	NW	...	96.0	62.0	1025.1	1021.5	2.0	1.0	9.2	17.6	No	No
81516	2010-06-03	Dartmoor	5.2	15.5	0.2	0.2	2.1	WNW	39.0	NaN	...	99.0	78.0	1027.2	1024.9	NaN	NaN	6.6	14.9	No	No
72005	2013-08-29	Mildura	14.8	27.6	0.0	5.4	5.0	NW	63.0	NE	...	26.0	13.0	1006.7	1002.0	7.0	1.0	20.5	26.3	No	No
131729	2013-12-02	Hobart	15.0	30.4	0.0	6.4	13.7	NNW	50.0	NNW	...	44.0	52.0	1012.7	1010.2	NaN	NaN	20.9	21.7	No	No
14699	2016-06-14	Moree	6.8	21.5	0.0	11.2	NaN	E	30.0	ESE	...	67.0	43.0	1034.4	1031.4	NaN	NaN	13.8	21.2	No	No
57961	2016-12-27	Ballarat	14.3	26.3	3.8	NaN	NaN	ESE	50.0	NNE	...	98.0	86.0	1011.5	1009.9	8.0	8.0	20.0	22.6	Yes	Yes

	Location	WindGustDir	day	month	year	MinTemp	MaxTemp	Rainfall	Evaporation	WindGustSpeed	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
0	2	13	1	11	0	13.4	22.9	0.6	NaN	44.0	71.0	22.0	1007.7	1007.1	8.0	NaN	16.9	21.8
1	2	14	1	11	1	7.4	25.1	0.0	NaN	44.0	44.0	25.0	1010.6	1007.8	NaN	NaN	17.2	24.3
2	2	15	1	11	2	12.9	25.7	0.0	NaN	46.0	38.0	30.0	1007.6	1008.7	NaN	2.0	21.0	23.2
3	2	4	1	11	3	9.2	28.0	0.0	NaN	24.0	45.0	16.0	1017.6	1012.8	NaN	NaN	18.1	26.5
4	2	13	1	11	4	17.5	32.3	1.0	NaN	41.0	82.0	33.0	1010.8	1006.0	7.0	8.0	17.8	29.7

	Location	WindGustDir	RainToday	RainTomorrow	day	month	year	MinTemp	MaxTemp	Rainfall	Evaporation	WindGustSpeed	Humidity9am	Humidity3pm	Pressure9am	Pressure3pm	Cloud9am	Cloud3pm	Temp9am	Temp3pm
0	2.0	13.0	0.0	0.0	1.0	11.0	0.0	13.4	22.9	0.6	5.978670	44.0	71.0	22.0	1007.7	1007.1	8.000000	5.039727	16.9	21.8
1	2.0	14.0	0.0	0.0	1.0	11.0	1.0	7.4	25.1	0.0	6.242761	44.0	44.0	25.0	1010.6	1007.8	1.776385	2.605029	17.2	24.3
2	2.0	15.0	0.0	0.0	1.0	11.0	2.0	12.9	25.7	0.0	8.273388	46.0	38.0	30.0	1007.6	1008.7	2.037233	2.000000	21.0	23.2
3	2.0	4.0	0.0	0.0	1.0	11.0	3.0	9.2	28.0	0.0	6.242160	24.0	45.0	16.0	1017.6	1012.8	1.371820	2.029181	18.1	26.5
4	2.0	13.0	0.0	0.0	1.0	11.0	4.0	17.5	32.3	1.0	7.194498	41.0	82.0	33.0	1010.8	1006.0	7.000000	8.000000	17.8	29.7
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
95	2.0	10.0	0.0	0.0	2.0	2.0	7.0	11.0	30.2	0.0	6.895401	24.0	54.0	20.0	1017.0	1014.7	1.857876	2.275389	17.6	28.8
96	2.0	5.0	0.0	0.0	2.0	2.0	8.0	13.8	31.8	0.0	7.556472	24.0	49.0	28.0	1019.7	1015.9	2.302235	2.598391	18.6	30.5
97	2.0	4.0	0.0	1.0	2.0	2.0	9.0	15.5	32.0	0.0	8.374073	50.0	51.0	25.0	1019.5	1016.2	3.150445	3.638528	20.1	30.8
98	2.0	4.0	1.0	0.0	2.0	2.0	10.0	18.4	30.5	1.2	7.175351	44.0	57.0	23.0	1021.3	1018.0	3.344974	2.861642	21.5	29.6
99	2.0	13.0	0.0	1.0	2.0	2.0	11.0	20.9	25.7	0.0	6.882608	37.0	52.0	90.0	1019.5	1018.9	6.130625	8.000000	22.2	18.8

	accuracy	balanced_accuracy	precision	w_precision	recall	w_recall	f1
Albero_Decisionale	0.983348	0.983347	0.980279	0.983367	0.986544	0.983348	0.983401
Albero_Decisionale_CV	0.967708	0.967707	0.964088	0.967736	0.971611	0.967708	0.967835
Naive_Bayes	0.841438	0.841439	0.85423	0.841884	0.823403	0.841438	0.838533
Naive_Bayes_CV	0.841438	0.841439	0.85423	0.841884	0.823403	0.841438	0.838533
LogReg	0.863501	0.8635	0.855009	0.863709	0.875477	0.863501	0.865122
LogReg_CV	0.870514	0.870513	0.863408	0.870656	0.880307	0.870514	0.871776
KNN	0.942987	0.942984	0.899253	0.948368	0.997764	0.942987	0.945951
KNN_CV	0.960325	0.960323	0.927289	0.963094	0.998988	0.960325	0.961804
SGD	0.82526	0.825252	0.749684	0.858076	0.976631	0.82526	0.84824
SGD_CV	0.840057	0.84005	0.770724	0.863933	0.968131	0.840057	0.858222
Voting	0.889349	0.889349	0.880198	0.889575	0.901398	0.889349	0.890672
Random_Forest	0.978792	0.978791	0.968255	0.979034	0.990045	0.978792	0.979029
AdaBoost	0.90905	0.909049	0.899862	0.909266	0.920549	0.90905	0.910088
XGBoost	0.986986	0.986986	0.990567	0.987012	0.983338	0.986986	0.986939

	accuracy	balanced_accuracy	precision	w_precision	recall	w_recall	f1
Albero_Decisionale	0.947412	0.947413	0.943833	0.947441	0.951433	0.947412	0.947618
Albero_Decisionale_CV	0.967708	0.967707	0.964088	0.967736	0.971611	0.967708	0.967835
Naive_Bayes	0.839689	0.839688	0.849414	0.839953	0.825731	0.839689	0.837405
Naive_Bayes_CV	0.839689	0.839688	0.849414	0.839953	0.825731	0.839689	0.837405
LogReg	0.862685	0.862687	0.853422	0.862934	0.875755	0.862685	0.864444
LogReg_CV	0.87033	0.870331	0.863039	0.870479	0.880337	0.87033	0.871602
KNN	0.922018	0.922026	0.868589	0.931072	0.994475	0.922018	0.927279
KNN_CV	0.932895	0.932902	0.883892	0.940062	0.996702	0.932895	0.936914
SGD	0.822624	0.82264	0.746668	0.856397	0.97653	0.822624	0.846268
SGD_CV	0.836563	0.836577	0.766626	0.861415	0.967665	0.836563	0.855493
Voting	0.883733	0.883735	0.870457	0.884226	0.901623	0.883733	0.885766
Random_Forest	0.959146	0.959147	0.948613	0.959399	0.970877	0.959146	0.959616
AdaBoost	0.907115	0.907116	0.899139	0.907278	0.917084	0.907115	0.908023
XGBoost	0.973877	0.973877	0.978175	0.973916	0.969378	0.973877	0.973757

	accuracy	balanced_accuracy	precision	w_precision	recall	w_recall	f1
ANN	0.962058	0.961971	0.951872	0.962303	0.973906	0.962058	0.962763
MLP	0.849796	0.849788	0.904027	0.856214	0.782646	0.849796	0.838969

Progetto Data Mining¶

About Dataset¶

Content¶

Informazioni di base e data visualization¶

Data cleaning e Pre-processing¶

Outlier detection¶

Correlazione e importanza delle features¶

Bilanciamento del dataset¶

Metriche per la valutazione dei risultati¶

Classificatori¶

Albero Decisionale¶

Risultati sul training set¶

Risultati sul test set¶

Albero decisionale (GridSearchCV)¶

Risultati Train Set¶

Risultati Test set¶

Naive Bayes¶

Risultati Train set¶

Risultati Test set¶

Naive Bayes (SearchGridCV)¶

Risutati Train set¶

Risultati Test set¶

Logistic Regression¶

Risultati sul Train set¶

Risultati Test set¶

Logistic Regression (GridSearchCV)¶

Risultati Train set¶

Risultati Test set¶

K Nearest Neighbors¶

Risultati Train set¶

Risultati Test Set¶

KNN (GridSearchCV)¶

Risultati Train Set¶

Risultati Test set¶

SGD¶

Risutlati Train set¶

Risultati Test set¶

SGD (GridSearchCV)¶

Risutlati Training set¶

Risultati Test set¶

Voting¶

Risultati Train Set¶

Risultati Test Set¶

Classificatori Ensemble¶

Random Forest¶

Risultati Train set¶

Risultati Test set¶

Boosting¶

Adaboost¶

Risultati Train set¶

Risultati Test set¶

XGBoost¶

Risultati Train set¶

Risultati Test set¶

Visualizzazione dei risultati¶

Accuracy¶

Precision¶

Recall¶

F1 Score¶

Rete neurale¶

ANN¶

Performance¶

MLP¶

Risultati Train set¶

Risultati Test set¶

Performance delle due Reti Neurali¶

Accuracy¶

F1 score¶

Precision¶

Recall¶